Decentralised Finance (DeFi) applications involve a large volume of funds and exhibit diverse user behaviours, including malicious activities such as smart contract exploits and financial scams. Existing approaches struggle to capture complex behaviours. To address this gap, we propose a general Blockchain User Behaviour Analysis (BUBA) pipeline for DeFi security. The pipeline presents an automated action formation process that takes blockchain transactions as inputs and outputs user actions. In addition, BUBA introduces a dual Graph Neural Network (GNN) model that jointly captures user action features, contract and token interactions, and heterogeneous graph structure information to produce rich behavioural embeddings, enabling effective clustering of semantically meaningful user behaviours. We evaluate the proposed pipeline on Uniswap V3, where it outperforms baseline methods in identifying and differentiating suspicious behaviours. A further case study on Sushiswap V2 demonstrates the generalisability of the pipeline across DeFi applications.
Oshani Seneviratne, Fernando Spadea, Adrien Pavao, Aaron Micah Green · 5 authors
Temporal Web analytics increasingly relies on large-scale, longitudinal data to understand how users, content, and systems evolve over time. A rapidly growing frontier is the \emph{Temporal Web3}: decentralized platforms whose behavior is recorded as immutable, time-stamped event streams. Despite the richness of this data, the field lacks shared, reproducible benchmarks that capture real-world temporal dynamics, specifically censoring and non-stationarity, across extended horizons. This absence slows methodological progress and limits the transfer of techniques between Web3 and broader Web domains. In this paper, we present the \textit{FinSurvival Challenge 2025} as a case study in benchmarking \emph{temporal Web3 intelligence}. Using 21.8 million transaction records from the Aave v3 protocol, the challenge operationalized 16 survival prediction tasks to model user behavior transitions.We detail the benchmark design and the winning solutions, highlighting how domain-aware temporal feature construction significantly outperformed generic modeling approaches. Furthermore, we distill lessons for next-generation temporal benchmarks, arguing that Web3 systems provide a high-fidelity sandbox for studying temporal challenges, such as churn, risk, and evolution that are fundamental to the wider Web.
Non-fungible tokens (NFTs) have become a key asset class in Web3 markets, where visual artwork, textual narratives, and on-chain transaction patterns jointly determine value, yet their pricing dynamics remain volatile, opaque, and difficult to explain. Existing NFT valuation methods typically either ignore the multimodal nature of NFTs or treat assets as independent samples, failing to exploit the rich relational structures induced by shared creators, collections, and ownership patterns, and offering limited interpretability for high-stakes financial decisions. To address these challenges, we propose NFT-Insight, a multimodal graph transformer framework that unifies visual, textual, and blockchain information on a heterogeneous NFT graph and explicitly links structural and content signals to valuation behavior. The framework identifies closely related NFTs via a joint similarity measure in the multimodal embedding space, propagates information through a relation-specific graph attention network and a global transformer encoder, and adopts a regularization strategy that encourages consistent valuations for highly similar assets while still allowing data-driven differentiation. In addition, NFT-Insight integrates attention-based and SHAP-based explanations into a unified analysis pipeline, enabling joint study of valuation behavior and feature attributions at the level of related NFT pairs. Experiments on three large-scale, real-world NFT datasets show that NFT-Insight consistently outperforms strong unimodal, multimodal, and graph-based baselines, reducing MAE and RMSE by up to about 20% in static valuation (withR2up to 0.904), achieving robust cross-market performance with averageR2≈ 0.84 andr≈ 0.93, and attainingR2= 0.911 in temporal forecasting. Interpretability analysis reveals that visual, textual, blockchain, and graph-relational features achieve a high alignment between SHAP importance and attention weights (average Spearman correlation above 0.8), and case studies highlight meaningful valuation patterns driven by rarity, speculative trading, and temporal market shocks. Overall, the proposed framework offers a multimodal graph–based perspective on explainable NFT valuation and market forecasting, and provides a general template for incorporating complex relational and content interactions into graph-based learning in decentralized digital economies.
Decentralised energy ecosystems suffer from data-governance, scalability and adoption barriers. Although blockchain-based marketplaces can offer transparency and security in Local Energy Communities (LECs), most existing solutions struggle with rigid token models, limited performance, and steep usability barriers. Building on a previous framework, this study presents an enhanced marketplace that integrates a modular blockchain layer, custodial identity management, and a dual-token model for flexible licensing and pricing. Testing on a per-missioned Quorum network with asynchronous queueing demonstrated notable improvements in transaction throughput and user responsiveness under load, while the custodial onboarding flow simplified access for non-technical participants. A refined policy enforcement mechanism further aligns the system with emerging federation standards, mitigating earlier shortcomings related to performance, data sovereignty, and scalability. Benchmarking on a five-node Quorum Proof of Authority (PoA) deployment (one RPC node and four validator nodes) showed that all key operations, including license issuance and asset usage, consistently completed in under 8 seconds, confirming the system’s suitability for possible energy data applications. Planned extensions include cross-domain interoperability, self-service governance tools, and zero-knowledge proofs, underscoring this architecture’s potential as a robust, future-ready platform for federated energy data ecosystems.
In order to solve the problem of low security of high network information sharing, the architecture and implementation of agent-based information sharing and pushing system are proposed. Firstly, the information node registration algorithm is introduced to draw the organization network connected to the public network into an orderly block network and extract the abnormal information of network nodes; Secondly, a complete network identity security threat intelligence is generated through effective scheduling and transmission of network identity security threat intelligence; Finally, the distributed ledger technology is introduced to match it with IP network, and the private chain and data are extracted by constructing data structure on the information chain to realize the generation and operation of intelligence information sharing model. The experimental results show that the model designed in this paper can protect the privacy information that all network users need to protect in the process of sharing information resources, and its privacy protection intensity exceeds 0.950. Conclusion: The proposed sharing model can realize the safe sharing of user intelligence information in practical application, and the user’s private intelligence information will not be leaked during the sharing process, which reduces the threat degree of network security.
Abstract In Web3 social platforms, i.e. social web applications that rely on blockchain technology to support their functionalities, interactions among users are usually multimodal, from common social interactions such as following, liking, or posting, to specific relations given by crypto-token transfers facilitated by the blockchain. In this dynamic and intertwined networked context, modeled as a financial network, our main goals are (i) to predict whether a pair of users will be involved in a financial transaction, i.e. the transaction prediction task , even using textual information produced by users, and (ii) to verify whether performances may be enhanced by textual content. To address the above issues, we compared current snapshot-based temporal graph learning methods and developed T3GNN, a solution based on state-of-the-art temporal graph neural networks’ design, which integrates fine-tuned sentence embeddings and a simple yet effective graph-augmentation strategy for representing content, and historical negative sampling. We evaluated models in a Web3 context by leveraging a novel high-resolution temporal dataset, collected from one of the most used Web3 social platforms, which spans more than one year of financial interactions as well as published textual content. The experimental evaluation has shown that T3GNN consistently achieved the best performance over time and for most of the snapshots. Furthermore, through an extensive analysis of the performance of our model, we show that, despite the graph structure being crucial for making predictions, textual content contains useful information for forecasting transactions, highlighting an interplay between users’ interests and economic relationships in Web3 platforms. Finally, the evaluation has also highlighted the importance of adopting sampling methods alternative to random negative sampling when dealing with prediction tasks on temporal networks.
Privacy and trust are highly demanding in practical recommendation engines. Although Federated Learning (FL) has significantly addressed privacy concerns, commercial operators are still worried about several technical challenges while bringing FL into production. In addition, classical FL has several intrinsic operational limitations such as single-point failure, data and model tampering, and heterogenic clients participating in the FL process. To address these challenges in practical recommenders, we propose a responsible recommendation generation framework based on blockchain-empowered asynchronous FL that can be adopted for any model-based recommender system. In standard FL settings, we build an additional aggregation layer in which multiple trusted nodes guided by a mediator component perform gradient aggregation to achieve an optimal model locally in a parallel fashion. The mediator partitions users into K clusters, and each cluster is represented by a cluster head. Once a cluster gets semi-global convergence, the cluster head transmits model gradients to the FL server for global aggregation. In addition the trusted cluster heads are responsible to submit the converged semi-global model to a blockchain to ensure tamper resilience. In our settings, an additional mediator component works like an independent observer that monitors the performance of each cluster head, updates a reward score, and records it into a digital ledger. Finally, evaluation results on three diversified benchmarks illustrate that the recommendation performance on selected measures is considerably comparable with the standard and federated version of a well-known neural collaborative filtering recommender.
Temporal Heterogeneous Networks (THNs) are evolving networks that characterize many real-world applications such as citation and events networks, recommender systems, and knowledge graphs. Forecasting THNs involves predicting future connections within a network that evolves over time and comprises diverse types of nodes and interactions with varying temporal dynamics. Although some Graph Neural Networks (GNNs) models have been successfully applied to forecast THNs, there is a lack of a general overview of how the message-passing computation could be extended to treat THNs. Moreover, most of the current solutions exhibit pitfalls in their training and evaluation strategies. Hence, in this work, we propose a graph deep learning framework for THN forecasting. Our framework decomposes the computation of a GNN layer into multiple components and introduces two different schemes to update embedding representations for THNs. This design allows the classification of existing solutions into special instances of our framework and highlights their potential limitations. We also extend the set of benchmarks for THNs by introducing two novel high-resolution temporal heterogeneous graph datasets derived from an emerging Web3 platform and a well-established e-commerce website. Overall, we conducted the first massive evaluation of THNs solutions over four temporal heterogeneous network datasets on two different future link prediction tasks using a fair newly introduced evaluation setting that considers the evolving nature of the data. Based on the limitations of existing solutions, we develop a new model that combines working techniques from previous models and leverages a new embedding update scheme. Experiments show the prediction power of our model compared to current solutions for link prediction in temporal graphs. Moreover, the experimental evaluation highlights the strengths and weaknesses of the different solutions and shows the effectiveness of our framework design.
Yong Eui Kim, Sang‐Min Choi, Dongwoo Lee, Yeong Geon Seo · 5 authors
Personalized recommender systems are used not only in e-commerce companies but also in various web applications. These systems conventionally use collaborative filtering (CF) and content-based filtering approaches. CF operates using memory-based or model-based methods; both methods use a user-item matrix that considers user preferences as items. This matrix denotes information on user preferences, which refers to the user ratings for items. The model-based method exploits the fact that the input matrix is factorized. CF approaches can effectively provide personalized recommendation results to users; however, cold-start problems arise because both these methods depend on the users’ ratings for items to predict users’ preferences. We proposed an approach to alleviate the cold-start problem along with a methodology for utilizing blockchain that can enhance the reliability of the processes of the recommendations. We attempted to predict an average rating for a new item to alleviate item-side cold-start problems. First, we applied the concept of word2vec, treating each user’s item-selection history as a sentence. Then, we derived genre2Vec based on the skip-gram technique and predicted an average rating for a new item by utilizing the vectors and category ratings. We experimentally demonstrated that our approach could generate more accurate results than conventional CF approaches could. We also designed the processes of the recommendation based on the concept of blockchain addressing the smart contract. Based on our approach, we proposed a system that can secure reliability as well as alleviate the cold-start problems in recommender systems.
Seonmi Kim, Y. C. Lee, Yejin Kim, Joohwan Hong · 5 authors
Recommender systems have become essential tools for enhancing user experiences across various domains. While extensive research has been conducted on recommender systems for movies, music, and e-commerce, the rapidly growing and economically significant Non-Fungible Token (NFT) market remains underexplored. The unique characteristics and increasing prominence of the NFT market highlight the importance of developing tailored recommender systems to cater to its specific needs and unlock its full potential. In this paper, we examine the distinctive characteristics of NFTs and propose the first recommender system specifically designed to address NFT market challenges. In specific, we develop a Multi-Attention Recommender System for NFTs (NFT-MARS) with three key characteristics: (1) graph attention to handle sparse user-item interactions, (2) multi-modal attention to incorporate feature preference of users, and (3) multi-task learning to consider the dual nature of NFTs as both artwork and financial assets. We demonstrate the effectiveness of NFT-MARS compared to various baseline models using the actual transaction data of NFTs collected directly from blockchain for four of the most popular NFT collections. The source code and data are available at https://anonymous.4open.science/r/RecSys2023-93ED.
Konstantin D. Pandl, Chun-Yin Huang, Ivan Beschastnikh, Xiaoxiao Li · 6 authors
Existing research on data valuation in federated and swarm learning focuses on valuing client contributions and works best when data across clients is independent and identically distributed (IID). In practice, data is rarely distributed IID. We develop an approach called DDVal for decentralized data valuation, capable of valuing individual data points in federated and swarm learning. DDVal is based on sharing deep features and approximating Shapley values through a k-nearest neighbor approximation method. This allows for novel applications, for example, to simultaneously reward institutions and individuals for providing data to a decentralized machine learning task. The valuation of data points through DDVal allows to also draw hierarchical conclusions on the contribution of institutions, and we empirically show that the accuracy of DDVal in estimating institutional contributions is higher than existing Shapley value approximation methods for federated learning. Specifically, it reaches a cosine similarity in approximating Shapley values of 99.969 % in both, IID and non-IID data distributions across institutions, compared with 99.301 % and 97.250 % for the best state of the art methods. DDVal scales with the number of data points instead of the number of clients, and has a loglinear complexity. This scales more favorably than existing approaches with an exponential complexity. We show that DDVal is especially efficient in data distribution scenarios with many clients that have few data points - for example, more than 16 clients with 8,000 data points each. By integrating DDVal into a decentralized system, we show that it is not only suitable for centralized federated learning, but also decentralized swarm learning, which aligns well with the research on emerging internet technologies such as web3 to reward users for providing data to algorithms.
Ranking algorithms in traditional search engines are powered by enormous training data sets that are meticulously engineered and curated by a centralized entity. Decentralized peer-to-peer (p2p) networks such as torrenting applications and Web3 protocols deliberately eschew centralized databases and computational architectures when designing services and features. As such, robust search-and-rank algorithms designed for such domains must be engineered specifically for decentralized networks, and must be lightweight enough to operate on consumer-grade personal devices such as a smartphone or laptop computer. We introduce G-Rank, an unsupervised ranking algorithm designed exclusively for decentralized networks. We demonstrate that accurate, relevant ranking results can be achieved in fully decentralized networks without any centralized data aggregation, feature engineering, or model training. Furthermore, we show that such results are obtainable with minimal data preprocessing and computational overhead, and can still return highly relevant results even when a user's device is disconnected from the network. G-Rank is highly modular in design, is not limited to categorical data, and can be implemented in a variety of domains with minimal modification. The results herein show that unsupervised ranking models designed for decentralized p2p networks are not only viable, but worthy of further research.
Non-Fungible Token (NFT) is a digital asset that cannot be exchanged or used, and uses Crypto currency values according to the type of digital money used, for example Bitcoin, Ethereum.The NFT Marketplace is a platform for buying and selling NFT like Tokopedia.This common problem is often encountered in e-commerce, especially in the NFT Marketplace, among other buyers often having difficulty finding products.This makes it difficult for the NFT Marketplace and sellers to promote products that match the preferences of potential buyers.A recommendation system that is very much needed in overcoming these problems, responding to these problems the author tries to make a recommendation system using the Content Based Filtering approach using the cosine similarity.The results of this study indicate that the Machine Learning model can provide Top-N recommendations from the product being sought.
Smart contracts on Ethereum evolve rapidly and lack explicit feedback, so it becomes necessary to use implicit feedback for recommendations. This paper proposes a collaborative filtering recommendation algorithm based on the user preferences list (UPLS-CF) to solve the above problems. We propose a pseudo rating generator to convert the implicit feedback data into explicit ratings and use collaborative filtering-based recommendation algorithm to complete top-N recommendations for smart contracts. In addition, we introduce user preference information to improve the accuracy of recommendations. Extensive experiments on datasets show that the algorithm proposed in this paper improves Precision by 15.975%, Recall by 12.116%, and HR by 20.815%. The results show that it can improve the algorithm's accuracy and can effectively recommend smart contracts to Ethereum users to combine the proposed algorithm with the user preference information.
Blockchain is an innovative distributed ledger technology that is widely used to build next-generation applications without the support of a trusted third party. With the ceaseless evolution of the service-oriented computing (SOC) paradigm, Blockchain-as-a-Service (BaaS) has emerged, which facilitates development of blockchain-based applications. To develop a high-quality blockchain-based system, users must select highly reliable blockchain services (peers) that offer excellent quality-of-service (QoS). Since the vast number of blockchain services leading to sparse QoS data, selecting the optimal personalized services is challenging. Hence, we improve neural collaborative filtering and propose a QoS-based blockchain service reliability prediction algorithm under BaaS, named modified neural collaborative filtering (MNCF). In this model, we combine a neural network with matrix factorization to perform collaborative filtering for the latent feature vectors of users. Furthermore, multi-task learning for sharing different parameters is introduced to improve the performance of the model. Experiments based on a large-scale real-world dataset validate its superior performance compared to baselines.
Graph neural networks (GNN) have been successful in many fields, and derived various researches and applications in real industries. However, in some privacy sensitive scenarios (like finance, healthcare), training a GNN model centrally faces challenges due to the distributed data silos. Federated learning (FL) is a an emerging technique that can collaboratively train a shared model while keeping the data decentralized, which is a rational solution for distributed GNN training. We term it as federated graph learning (FGL). Although FGL has received increasing attention recently, the definition and challenges of FGL is still up in the air. In this position paper, we present a categorization to clarify it. Considering how graph data are distributed among clients, we propose four types of FGL: inter-graph FL, intra-graph FL and graph-structured FL, where intra-graph is further divided into horizontal and vertical FGL. For each type of FGL, we make a detailed discussion about the formulation and applications, and propose some potential challenges.
Ge Chen, Jun Wu, Wu Yang, Ali Kashif Bashir · 6 authors
Nowadays, adopting blockchain technology to Internet of Things has become a trend and it is important to minimize energy consumption while providing a high quality of service (QoS) in Blockchain-based IoT networks. Pre-caching popular and fresh IoT content avoids activating sensors frequently, thus effectively reducing network energy consumption. However, the user equipment in regions covered by base stations will generate distributed and time-varying data requests, hence modeling the base station topology to capturing spatio-temporal request patterns is required for the data storage pre-allocation. Traditional solutions typically fail to pay attention to the topology, resulting in the sensor being activated redundantly. In this paper, we propose Request Graph Convolutional-LSTM to capture the spatio-temporal request patterns in Blockchain-based IoT networks and make predictions. Moreover, a heuristic algorithm based on the predictions is proposed to develop pre-caching strategy, which determines the data and location to be cached to minimize the mean data retrieval latency restricted by the cache space of IoT network entities and the freshness of IoT content. Experiments show that our proposed frame provides a low energy consumption.
Andrea Lisi, Andrea De Salve, Paolo Mori, Laura Ricci · 5 authors
Recommender Systems (RSs) are becoming increasingly popular in the last years. They collect reviews concerning several types of items (e.g., shops, professionals, services, songs or videos) in order to rank them according to a given criterion, and to suggest the most relevant ones to their users. However, most of the currently used RSs exhibit two main drawbacks: they are based on a centralized control model and they do not provide reward mechanisms to encourage the participation of users. To deal with these challenges, the architectures of current RSs could be enhanced through blockchain technology, thus providing novel solutions to decentralize them. As a matter of fact, the blockchain technology could be successfully adopted in this context because smart contracts would allow the decentralization of system control, while cryptocurrency and tokens could be used to implement the reward mechanism. In the light of the above considerations, this manuscript presents a decentralized rating framework aimed to support the users of RSs based on blockchain technology, providing a token-based reward mechanism that remunerates users submitting their reviews to incentivize their participation. Moreover, the proposed system provides a flexible strategy to rank items, allowing users to choose among different functions to combine reviews to obtain item ranking. The performance and the cost of using the proposed system have been evaluated on the Ropsten Ethereum test network. For instance, our experiments have shown that the median time required to store a batch of 35 ratings is about 47 s, while the average time required to obtain the score of an item having 6000 ratings is less than 2.5 s.
Graph convolutional networks (GCNs) have been employed as a kind of significant tool on many graph-based applications recently. Inspired by convolutional neural networks (CNNs), GCNs generate the embeddings of nodes by aggregating the information of their neighbors layer by layer. However, the high computational and memory cost of GCNs due to the recursive neighborhood expansion across GCN layers makes it infeasible for training on large graphs. To tackle this issue, several sampling methods during the process of information aggregation have been proposed to train GCNs in a mini-batch Stochastic Gradient Descent (SGD) manner. Nevertheless, these sampling strategies sometimes bring concerns about insufficient information collection, which may hinder the learning performance in terms of accuracy and convergence. To tackle the dilemma between accuracy and efficiency, we propose to use aggregators with different granularities to gather neighborhood information in different layers. Then, a degree-based sampling strategy, which avoids the exponential complexity, is constructed for sampling a fixed number of nodes. Combining the above two mechanisms, the proposed model, named Mix-grained GCN (MG-GCN) achieves state-of-the-art performance in terms of accuracy, training speed, convergence speed, and memory cost through a comprehensive set of experiments on four commonly used benchmark datasets and a new Ethereum dataset.
Alexander Mikroyannidis, Allan Third, John Domingue
Blockchain technology provides a decentralised peer-to-peer infrastructure, supporting openness, transparency, accountability, identity management and trust. As such, the Blockchain has the potential to revolutionise education in a number of ways. Blockchain technology offers opportunities to thoroughly rethink how we find educational content and training services online, how we register and pay for them, as well as how we get accredited for what we have learned and how this accreditation affects our career trajectory. This paper explores a case study on the decentralisation of lifelong learning using Blockchain technology. In particular, we investigate the different scenarios and requirements for making online education and lifelong learning more open and decentralised, while placing lifelong learners in control of their learning process and its associated data. Additionally, we discuss various approaches to the Semantic Blockchain and the applications of these approaches on education.
Personalized quality of service (QoS) prediction plays an important role in helping users build high-quality service-oriented systems. To obtain accurate prediction results, many approaches have been investigated in recent years. However, these approaches do not fully address untrustworthy QoS values submitted by unreliable users, leading to inaccurate predictions. To address this issue, inspired by blockchain with distributed ledger technology, distributed consensus mechanisms, encryption algorithms, etc., we propose a personalized QoS prediction method for web services that we call blockchain-based matrix factorization (BMF). We develop a user verification approach based on homomorphic hash, and use the Byzantine agreement to remove unreliable users. Then, matrix factorization is employed to improve the accuracy of predictions and we evaluate the proposed BMF on a real-world web services dataset. Experimental results show that the proposed method significantly outperforms existing approaches, making it much more effective than traditional techniques.
Raheleh Hassannia, Ali Vatankhah Barenji, Zhi Li, Habib Alipour
The purpose of the study is to design and develop a recommended system based on agent and web technologies, which utilizes a hybrid recommendation filtering for the smart tourism industry. A hybrid recommendation system based on agent technology is designed by considering the online communication with other sectors in the tourism industry, such as the tourism supply chain, agency etc. However, online communication between the sectors via agents is designed and developed based on the contract net protocol. Furthermore, the design system is developed on the java agent development framework and implemented as a web application. Case study-based results considering two scenarios involving 100 customers illustrated that the proposed web application improves the rate of the recommendation for the customers. In the first scenario without disturbances, this rate was improved by 20% and the second scenario with disturbances yielded a 30% rate of acceptable recommendation. In addition, based on the second scenario, real time data communication on the system occurred, thus the proposed system supported real time data communication.
Since first coined by Google in 2012, knowledge graph has received extensive attention from both industry and academia, and has been widely used in many scenarios with success, e.g. information retrieval, online recommendation, question-answering, and so on. However, traditional centralized construction of knowledge graph faces many challenges, such as laborious and time-consuming, vulnerable to manipulation or tampering, lacking scrutiny, among others. Therefore, in this paper, we propose a novel decentralized knowledge graph construction method by means of crowdsourcing, and the business logic of crowdsourcing is implemented by blockchain-powered smart contracts to guarantee the transparency, integrity, and auditability. On this basis, the decentralized knowledge graph is used for a deep recommender system, and case studies validate the effectiveness of the system. This paper is aimed at providing a novel decentralized approach for constructing knowledge graph and serving as reference and guidance for future research and practical applications of knowledge graph.
As data generation becomes increasingly inherently distributed, either due to usergenerated (multimedia) content or because of application-specific needs (sensor networks, data streams, etc.), traditional centralized architectures fail to address the new challenges of contemporary data management.A promising solution for the design and deployment of global-scale applications is the exploitation of the peer-to-peer (P2P) paradigm.P2P has emerged as a powerful model for organizing and searching large data repositories distributed over autonomous independent sources.The main topic and contribution of this thesis is the unsupervised organization of content into Semantic Overlay Networks (SONs), in a decentralized and distributed manner, and subsequently a variety of techniques for efficient searching and query processing in unstructured P2P systems.SONs have been proposed in the relevant research literature, as a way to organize peers into thematic groups, thereby enabling query routing to specific peer groups in a deliberate way, instead of blind forwarding.In particular, this work focuses on unstructured P2P networks that preserve peer autonomy.A novel protocol for unsupervised, distributed and decentralized SON construction is proposed, named DESENT [35,38], which employs distributed clustering of peer contents, respecting the requirements imposed by the distributed nature of the environment [138].Exploiting the generated SONs, we propose efficient routing strategies for answering similarity search queries [37,39].The approach is applied and tested in a distributed IR setting, aiming to address some of the limitations of P2P IR/web search.Towards this goal, a distributed dimensionality reduction algorithm is proposed [96], in order to reduce the high-dimensional feature space and improve clustering quality.Assuming a super-peer architecture we propose an approach called SIMPEER [43] that efficiently supports similarity search over data distributed over a large set of peers.We show how range queries and nearest neighbor queries can be processed.We also explore how to support non-traditional queries (such as top-k [141] and skylines [139]) that involve ranking.Furthermore, by relaxing the restriction of completely unsupervised environment and assuming a semi-supervised context, a novel technique for P2P summary caching of hierarchical information is presented, exploiting either predefined taxonomies [104] or XML schema information [36,40], which is applied in mobile P2P context-aware environments to improve query routing [45,44].6.4 Measurements from using different number of querying peers, given as the fraction of peers in the network. . . . . . . . . . . . . . . . .6.5 Measurements from using different skew (represented by increasing values of a) in the query distributions. . . . . . . . . . . . . . . . . .6.6 Measurements for different network