Tieliang Gao, Li Duan, Lufeng Feng, Wei Ni · 5 authors
Service composition platforms play a crucial role in creating personalized service processes. Challenges, including the risk of tampering with service data during service invocation and the potential single point of failure in centralized service registration centers, hinder the efficient and responsible creation of service processes. This paper presents a novel framework called Context-Aware Responsible Service Process Creation and Recommendation (SPCR-CA), which incorporates blockchain, Recurrent Neural Networks (RNNs), and a Skip-Gram model holistically to enhance the security, efficiency, and quality of service process creation and recommendation. Specifically, the blockchain establishes a trusted service provision environment, ensuring transparent and secure transactions between services and mitigating the risk of tampering. The RNN trains responsible service processes, contextualizing service components and producing coherent recommendations of linkage components. The Skip-Gram model trains responsible user-service process records, generating semantic vectors that facilitate the recommendation of similar service processes to users. Experiments using the Programmable-Web dataset demonstrate the superiority of the SPCR-CA framework to existing benchmarks in precision and recall. The proposed framework enhances the reliability, efficiency, and quality of service process creation and recommendation, enabling users to create responsible and tailored service processes. The SPCR-CA framework offers promising potential to provide users with secure and user-centric service creation and recommendation capabilities.
Federated recommendation systems (FRecSys) alleviate the privacy issues of recommendation systems (RecSys) by distributing model training tasks onto users’ local devices. However, they still need a single global server to aggregate training results from users and, thereby are vulnerable to server malfunctioning. Besides, they assume all users voluntarily use their data and computing resources to train recommendation model gradients, which is usually impractical. This paper aims to address the aforementioned problems of FRecSys using blockchain. A blockchain-based federated matrix factorization is designed and realized for RecSys, named BFRecSys. It eliminates the need for a single central server by storing the items and user matrices of the matrix factorization in a blockchain. An incentive mechanism is designed and implemented via smart contracts to record participants’ contributions. Besides, to further enhance the fairness of the incentive mechanism, a fake gradients detection mechanism based on an unsupervised cluster is designed to evict fake gradients in each iteration. The prototype of BFRecSys is realized, and experiments are carried out on public MovieLens datasets and private Ethereum blockchain. The results show that BFRecSys can significantly improve recommendation performance in terms of training accuracy.
Vertical Federated Learning (VFL) effectively addresses the issue of data isolation, which makes data mining secure. Most VFL implementations rely on a single server or third party for training, which will be terminated if the server or third party fails. In addition, the model accuracy trained by VFL depends on the quality of the client’s local features; nevertheless, the client’s local feature quality is difficult to verify. There exists a chance that the features owned by the client are irrelevant to the model or the intermediate results submitted by the client are inaccurate, such that the model’s accuracy will be seriously affected. In order to solve the single point failure and model accuracy issues in VFL, this paper first proposes a Blockchain – based Decentralized VFL (BDVFL) training model. With the integration of blockchain and the VFL training process, the nodes within the blockchain are categorized into non-training and training nodes. Our method focuses on the scenario in which all training nodes possess labeled data and actively engage in the training procedure of VFL. To be specific, first, each client utilizes local features and initial models to carry out forward activation and generate intermediate results. Second, we randomly choose a training node and combine it with the intermediate results from all clients to formulate the loss function. Finally, each client updates the local model by using the gradient. To protect the raw features, a blinding factor is utilized for safeguarding the intermediate results submitted by the client, such that the training nodes cannot infer the local features from intermediate results. To mitigate the interference of irrelevant training outcomes from clients on the model’s accuracy, we propose a verifiable aggregation method to assess the validity of the intermediate results submitted by the clients. We have conducted both theoretical and experimental analysis, and the results demonstrate the effectiveness of the proposed method.
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.
Over the past few years, personalized recommendations have emerged as a fundamental component of the consumer electronics sector. The rise of decentralized federated learning has expanded the horizons of personalized recommendations, offering significant potential. Nonetheless, the utilization of confidential data from diverse clients raises legitimate concerns regarding privacy and security. In response to these challenges, we present an innovative framework for secure and privacy-preserving decentralized federated learning, tailored to personalized recommendations within the consumer electronics sector. Our approach strives to facilitate the collective contribution of data from multiple clients to the learning process while safeguarding their privacy. To accomplish this, we harness the power of homomorphic encryption, ensuring that clients’ data remains encrypted and impervious to prying eyes. Additionally, we leverage blockchain technology to establish a secure, decentralized foundation for data exchange and management. Through the utilization of blockchain, we empower clients to validate the integrity of the learning process, guarantee system transparency, and thwart any malicious attempts at result manipulation. Our framework is rigorously assessed using real-world consumer electronics data, highlighting its capacity to provide a secure, decentralized, and privacy-centric solution for personalized recommendations. This approach not only enriches the user experience but also offers robust safeguards for sensitive data.
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.
Elisha Gras, Rosmi George, Kington Churchill, M Kiruthika
Structured data analysis has historically achieved remarkable success. However, the analysis of massive amounts of unstructured video data is still a challenging problem. Over one billion people use YouTube, a Google corporation, which generates billions of views. YouTube data is being created in extremely large quantities, and with a massive demand to store, analyze, and carefully study large amounts of data to make it usable for big data analytics. For the analysis of these YouTube data, the absence of YouTube Shorts which has become a current trend is the limitation. To address this limitation, YouTube Shorts along with traditional duration videos have been considered for analysis in this work. For analyzing these data, various Machine Learning (ML) techniques like clustering and classification have been considered to categorize the content creators into three different categories such as highly rated, moderately rated and lowly rated. These ratings for recommendation assist content creators in enhancing the value of their brand and the users are benefited by consuming, exchanging shares and promoting the content. The results observed show that the accuracy of the Random Forrest and Gradient Boosting classifiers have equivalent performance i.e., around 98% which are suitable for the above recommendation system. Hence, the objective to encourage investors and fans to become active stakeholders and owners of the creator’s micro-economy is addressed in this paper.
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.
This research explores the methods that Non-fungible Token (NFT)s can be recommended to people who inter-act with NFT-marketplaces to explore NFTs of preference and similarity to what they have been searching for. While exploring past methods that can be adopted for recommendations, the use of NFT traits for recommendations has been explored. The outcome of the research highlights the necessity of using multiple Recommender Systems to present the user with the best possible NFTs when interacting with decentralized systems.
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.
Rabeya Bosri, Mohammad Shahriar Rahman, Md Zakirul Alam Bhuiyan, Abdullah Al Omar
Data privacy is one of the intriguing problems in e-commerce site. For personal or business purposes, users have to disclose their private data to these e-commerce sites. Often such businesses use these highly sensitive data for computing artificial intelligence-driven analyses like recommendation generation without user consent. In the case of recommendation generation, data need to be analyzed at the business platforms. An automated personalization, based on artificial intelligence, on a list of products with respect to user interest is generated by a recommender system. However, the secure utilization of user data is absent in such systems. This paper proposes Private-Rec, a privacy-preserving platform for a recommendation system through the integration of artificial intelligence and blockchain. In Private-Rec, blockchain gives the user a secure environment through the distributed attribute in which data can be used with the required permission. Under this platform, users receive incentives (i.e., point, discount) from the recommended company for sharing their data to be used for computing recommendations. The Private-Rec platform has been studied empirically.
Blockchain-as-a-service (BaaS) experienced a dramatical growth in recent years, making it a hot research topic. With the expanding scale of distributed services deployed on the blockchain system, it is increasingly urgent to evaluate quality of service (QoS) attributes of blockchain services and in-blockchain peers-clients connections. The complicated association of service invocation and network environment naturally form a graph, making it possible to extract features through graph neural networks (GNN). To incorporate graph-structured information in QoS prediction, we proposed a graph matrix factorization (GraphMF) take advantages of both GNNs and collaborative filtering to estimate missing QoS values in the data matrix. Experiment conducted on a real-world dataset demonstrated the effectiveness of our model.
Hongman Wang, Yingxue Li, Xiaoqi Zhao, Fangchun Yang
Reasonable allocation of storage and computing resources is the basis of building big data system. With the development of IoT (Internet of Things), more data will be brought. A three-layer architecture includes smart devices layer, edge cloud layer and blockchain-based distributed cloud layer. Blockchain is used in IoT for building a distributed decentralize P2P architecture to deal with the secure issue while edge computing deals with increasing volume of data. Edge caching is one of the important application scenarios. In order to allocate edge cache resources reasonably, to improve the quality of service and to reduce the waste of bandwidth resources, this paper proposes a content selection algorithm of edge cache nodes. The algorithm adopts markov chain model, improves the utilization of cache space and reduces the content transmission delay. The hierarchical caching strategy is adopted and the secondary cache stores slides of contents to expand the coverage of cached content and to reduce user waiting time. Regional node cooperation is adopted to expand the cache space and to support the regional preference of cache content. Compared with the classical substitution algorithm, simulation results show that the algorithm in this paper has higher cache hit ratio and higher space utilization.
The interest in the blockchain technology has been increasing since its inception and it has been applied to many fields and sectors. The blockchain technology creates a decentralized environment where no third party controls the data and transaction. Mobile apps recommendation has been extensively used to recommend apps to mobile users. For example, Android-based recommendation applications have been developed to recommend other mobile apps for download depending on user’s preferences and mobile context. These recommendations help users discover apps by referring to the experiences of other users. Due to the collection of a large amount of data and user information, there is a problem of insecurity and user’s privacy that are prone to be attacked. To address this issue the blockchain technology can be incorporated to assure cryptographic safety. In this paper, we present a survey of the on-going mobile app recommendations and e-commerce technology trend to address how the blockchain can be incorporated into the collaborative filtering recommendation systems to enable the users to set up a secured data, which implies the importance of user privacy preference on personalized app recommendations.