ACM Transactions on the Web最新文献

Social network alignment, which aims to uncover the correspondence across different social networks, shows fundamental importance in a wide spectrum of applications such as cross-domain recommendation and information propagation. In the literature, the vast majority of the existing studies focus on the social network alignment at user level. In practice, the user-level alignment usually relies on abundant personal information and high-quality supervision, which is expensive and even impossible in the real-world scenario. Alternatively, we propose to study the problem of social group alignment across different social networks, focusing on the interests of social groups rather than personal information. However, social group alignment is non-trivial and faces significant challenges in both (i) feature inconsistency across different social networks and (ii) group discovery within a social network. To bridge this gap, we present a novel GroupAligner, a deep reinforcement learning with domain adaptation for social group alignment. In GroupAligner, to address the first issue, we propose the cycle domain adaptation approach with the Wasserstein distance to transfer the knowledge from the source social network, aligning the feature space of social networks in the distribution level. To address the second issue, we model the group discovery as a sequential decision process with reinforcement learning in which the policy is parameterized by a proposed proximity-enhanced Graph Neural Network (pGNN) and a GNN-based discriminator to score the reward. Finally, we utilize pre-training and teacher forcing to stabilize the learning process of GroupAligner. Extensive experiments on several real-world datasets are conducted to evaluate GroupAligner, and experimental results show that GroupAligner outperforms the alternative methods for social group alignment.

Device-level security has become a major concern in smart home systems. Detecting problems in smart home sytems strives to increase accuracy in near real time without hampering the regular tasks of the smart home. The current state of the art in detecting anomalies in smart home devices is mainly focused on the app level, which provides a basic level of security by assuming that the devices are functioning correctly. However, this approach is insufficient for ensuring the overall security of the system, as it overlooks the possibility of anomalies occurring at the lower layers such as the devices. In this article, we propose a novel notion, correlated graph, and with the aid of that, we develop our system to detect misbehaving devices without modifying the existing system. Our correlated graphs explicitly represent the contextual correlations among smart devices with little knowledge about the system. We further propose a linkage path model and a sensitivity ranking method to assist in detecting the abnormalities. We implement a semi-automatic prototype of our approach, evaluate it in real-world settings, and demonstrate its efficiency, which achieves an accuracy of around 90% in near real time.

Modelling the dynamic interactions between users and items on knowledge graphs is very crucial for improving the accuracy of recommendation. Although existing methods have made great progress in modelling the dynamic knowledge graphs for recommendation, they usually only consider the mutual influence between users and items involved in the interactions, and ignore the influence propagation from the interacting nodes (i.e., users and items) on dynamic knowledge graphs. In this paper, we propose an influence propagation-enhanced deep coevolutionary method for recommendation, which can capture not only the direct mutual influence between interacting users and items but also influence propagation from multiple interacting nodes to their high-order neighbors at the same time on the dynamic knowledge graph. Specifically, the proposed model consists of two main components: direct mutual influence component and influence propagation component.The former captures direct interaction influence between the interacting users and items to generate the effective representations for them. The latter refines their representations via aggregating the interaction influence propagated from multiple interacting nodes. In this process, a neighbor selection mechanism is designed for selecting more effective propagation influence, which can significantly reduce the computational cost and accelerate the training. Finally, the refined representations of users and items are used to predict which item the user is most likely to interact with. The experimental results on three real-world datasets illustrate that the effectiveness and robustness of PIDKG outperform all the state-of-the-art baselines and the efficiency of it is faster than most of comparative baselines.

Various opportunities are available to depict different domains due to the diverse nature of social networks and researchers' insatiable. An opinion leader is a human entity or cluster of people who can redirect human assessment strategy by intellectual skills in a social network. A more comprehensive range of approaches is developed to detect opinion leaders based on network-specific and heuristic parameters. For many years, deep learning–based models have solved various real-world multifaceted, graph-based problems with high accuracy and efficiency. The Graph Neural Network (GNN) is a deep learning–based model that modernized neural networks’ efficiency by analyzing and extracting latent dependencies and confined embedding via messaging and neighborhood aggregation of data in the network. In this article, we have proposed an exclusive GNN for Opinion Leader Identification (GOLI) model utilizing the power of GNNs to categorize the opinion leaders and their impact on online social networks. In this model, we first measure the n-node neighbor's reputation of the node based on materialized trust. Next, we perform centrality conciliation instead of the input data's conventional node-embedding mechanism. We experiment with the proposed model on six different online social networks consisting of billions of users’ data to validate the model's authenticity. Finally, after training, we found the top-N opinion leaders for each dataset and analyzed how the opinion leaders are influential in information diffusion. The training-testing accuracy and error rate are also measured and compared with the other state-of-art standard Social Network Analysis (SNA) measures. We determined that the GNN-based model produced high performance concerning accuracy and precision.

Despite the importance and pervasiveness of Wikipedia as one of the largest platforms for open knowledge, surprisingly little is known about how people navigate its content when seeking information. To bridge this gap, we present the first systematic large-scale analysis of how readers browse Wikipedia. Using billions of page requests from Wikipedia’s server logs, we measure how readers reach articles, how they transition between articles, and how these patterns combine into more complex navigation paths. We find that navigation behavior is characterized by highly diverse structures. Although most navigation paths are shallow, comprising a single pageload, there is much variety, and the depth and shape of paths vary systematically with topic, device type, and time of day. We show that Wikipedia navigation paths commonly mesh with external pages as part of a larger online ecosystem, and we describe how naturally occurring navigation paths are distinct from targeted navigation in lab-based settings. Our results further suggest that navigation is abandoned when readers reach low-quality pages. Taken together, these insights contribute to a more systematic understanding of readers’ information needs and allow for improving their experience on Wikipedia and the Web in general.

The prosperity of knowledge graphs (KG), as well as related downstream applications, have raised the urgent request of knowledge graph completion techniques for fully supporting the KG reasoning tasks, especially under the circumstance of training data scarcity. Though large efforts have been made on solving this challenge via few-shot learning tools, they mainly focus on simply aggregating entity neighbors to represent few-shot references, while the enhancement from latent semantic correlation within neighbors has been largely ignored. To that end, in this paper, we propose a novel few-shot learning solution, named as Semantic Interaction Matching network (SIM), which applies Transformer framework to enhance the entity representation with capturing semantic interaction between entity neighbors. Specifically, we first design entity-relation fusion module to adaptively encode neighbors with incorporating relation representation. Along this line, Transformer layers are integrated to capture latent correlation within neighbors, as well as the semantic diversification of the support set. Finally, a similarity score is attentively estimated with attention mechanism. Extensive experiments on two public benchmark datasets demonstrate that our model outperforms a variety of state-of-the-art methods with a significant margin.

We present a measurement study on compositions of Decentralized Finance (DeFi) protocols, which aim to disrupt traditional finance and offer services on top of distributed ledgers, such as Ethereum. Understanding DeFi compositions is of great importance, as they may impact the development of ecosystem interoperability, are increasingly integrated with web technologies, and may introduce risks through complexity. Starting from a dataset of 23 labeled DeFi protocols and 10,663,881 associated Ethereum accounts, we study the interactions of protocols and associated smart contracts. From a network perspective, we find that decentralized exchange (DEX) and lending protocol account nodes have high degree and centrality values, that interactions among protocol nodes primarily occur in a strongly connected component, and that known community detection methods cannot disentangle DeFi protocols. Therefore, we propose an algorithm to decompose a protocol call into a nested set of building blocks that may be part of other DeFi protocols. This allows us to untangle and study protocol compositions. With a ground truth dataset that we have collected, we can demonstrate the algorithm’s capability by finding that swaps are the most frequently used building blocks. As building blocks can be nested, that is, contained in each other, we provide visualizations of composition trees for deeper inspections. We also present a broad picture of DeFi compositions by extracting and flattening the entire nested building block structure across multiple DeFi protocols. Finally, to demonstrate the practicality of our approach, we present a case study that is inspired by the recent collapse of the UST stablecoin in the Terra ecosystem. Under the hypothetical assumption that the stablecoin USD Tether would experience a similar fate, we study which building blocks — and, thereby, DeFi protocols — would be affected. Overall, our results and methods contribute to a better understanding of a new family of financial products.