Graph structures are widely used to model relational data. In many real-world applications, each data client usually holds only a partial subgraph of the original graph, and privacy concerns limit data exchange between clients. This decentralized data distribution often degrades the effectiveness of conventional Graph Neural Networks (GNNs). Recently, subgraph federated learning has been proposed to enable subgraph data collaborative training without compromising privacy. However, two critical challenges remain: (1) Missing links between subgraphs from different clients significantly prevent the message-passing process in GNNs. (2) Varying data distributions across subgraphs lead to the non-IID issue (e.g., node label skews), which require personalization of local clients in subgraph federated learning scenarios. To address these challenges, we propose FedGC, a novel subgraph federated method that combines pseudo label-based client grouping with Local-Global Contrastive Tasks. Specifically, FedGC initializes a random graph on the server, leverages predicted pseudo label distributions to group clients, and assigns aggregation weights based on the similarity of these distributions. Additionally, FedGC incorporates Local-Global Contrastive tasks into the local client learning process to achieve personalized client parameter update. By adjusting the balance between local supervision task and contrastive task, FedGC enables each client to effectively control the balance of local and global information. Extensive experiments on six real-world datasets that cover citation networks and social networks validate the superior performance of FedGC compared to state-of-the-art baselines.

Finding experts is essential in Community Question Answering (CQA) platforms as it enables the effective routing of questions to potential users who can provide relevant answers. The key is to personalized learning expert representations based on their historical answered questions, and accurately matching them with target questions. Recently, the applications of Pre-Trained Language Models (PLMs) have gained significant attraction due to their impressive capability to comprehend textual data, and are widespread used across various domains. There have been some preliminary works exploring the usability of PLMs in expert finding, such as pre-training expert or question representations. However, these models usually learn pure text representations of experts from histories, disregarding personalized and fine-grained expert modeling. For alleviating this, we present a personalized pre-training and fine-tuning paradigm, which could effectively learn expert interest and expertise simultaneously. Specifically, in our pre-training framework, we integrate historical answered questions of one expert with one target question, and regard it as a candidate-aware expert-level input unit. Then, we fuse expert IDs into the pre-training for guiding the model to model personalized expert representations, which can help capture the unique characteristics and expertise of each individual expert. Additionally, in our pre-training task, we design (1) a question-level masked language model task to learn the relatedness between histories, enabling the modeling of question-level expert interest; (2) a vote-oriented task to capture question-level expert expertise by predicting the vote score the expert would receive. Through our pre-training framework and tasks, our approach could holistically learn expert representations including interests and expertise. Our method has been extensively evaluated on six real-world CQA datasets, and the experimental results consistently demonstrate the superiority of our approach over competitive baseline methods.

Achieving the generalization of an invariant classifier from training domains to shifted test domains while simultaneously considering model fairness is a substantial and complex challenge in machine learning. Existing methods address the problem of fairness-aware domain generalization, focusing on either covariate shift or correlation shift, but rarely consider both at the same time. In this paper, we introduce a novel approach that focuses on learning a fairness-aware domain-invariant predictor within a framework addressing both covariate and correlation shifts simultaneously, ensuring its generalization to unknown test domains inaccessible during training. In our approach, data are first disentangled into content and style factors in latent spaces. Furthermore, fairness-aware domain-invariant content representations can be learned by mitigating sensitive information and retaining as much other information as possible. Extensive empirical studies on benchmark datasets demonstrate that our approach surpasses state-of-the-art methods with respect to model accuracy as well as both group and individual fairness.

Graph contrastive learning (GCL), as a popular self-supervised learning technique, has demonstrated promising capability in learning discriminative representations for diverse downstream tasks. A large body of GCL frameworks mainly work on graphs formed under homophily effect, i.e., similar nodes tend to connect with each other. In their design, the augmentation and aggregation are usually conducted indiscriminately on edges, ignoring the existence of heterophilic edges that connect dissimilar nodes. Therefore, the efficacy of GCL could greatly deteriorate on heterophilic graphs, verified by our analysis: GCL on a mixture of homophilic and heterophilic edges will generate representations that are indistinguishable across different classes in the embedding space. To address this challenge, we propose a novel GCL framework via interventional view generation. Specifically, we generate homophilic and heterophilic views through counterfactual intervention, which targets on disentangling homophilic and heterophilic structure from the original graph, such that we can capture their corresponding information using separate filters in the contrastive learning process. Since the homophilic view and the heterophilic view present different frequency signals, they are further encoded via a low-pass and a high-pass filter respectively. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness of our design. Our proposed framework achieves a remarkably improved downstream performance on graphs with high heterophily while maintaining a comparable ability in learning homophilic graphs. A comprehensive study also verifies the necessity of individual designs in our framework.

This paper proposes a class of graph rules for deducing associations between entities, referred to as Graph Rules with Oracles and denoted by GROs. As opposed to previous graph rules, GROs support oracle functions to import (a) external knowledge, and (b) internal computations such as aggregate operators and machine learning predicates, and so on. Moreover, the semantics of GROs are defined in terms of pivoted dual simulation, in contrast to the subgraph isomorphism. We show how GROs can be used to predict links and catch anomalies, among other things. We formalize the association deduction problem with GROs in terms of the chase, and prove their Church-Rosser property. We show that both the deduction and incremental deduction problems with GROs are in PTIME, as opposed to the intractability of their counterparts with prior graph rules. We also provide sequential and parallel algorithms for association deduction and incremental deduction. Using real-life and synthetic graphs, we experimentally verify the effectiveness, scalability, and efficiency of the algorithms.

Personalized news recommendation aims to help users find news content they prefer, which has attracted increasing attention recently. There are two core issues in news recommendation: learning news representation and matching candidate news with user interests. In this context, “candidate” indicates potential for interest. Due to the superior ability to understand natural language demonstrated by Pretrained Language Models (PLMs), recent works utilize PLMs (e.g., BERT) to strengthen news modeling, obtaining more accurate user interest matching and achieving notable improvement in news recommendation. However, the existing PLM-based methods are usually incapable of fully exploring the fine-grained (i.e., word-level) relatedness between user behaviors and candidate news due to the heavy computational cost brought by PLMs. In this article, we propose a group-based personalized news recommendation method with long- and short-term matching mechanisms between users and candidate news based on PLMs to learn fine-grained matching efficiently and effectively. In our approach, we design to group user historical clicked news into chunks with quite shorter news sequences according to their clicked timestamps, which could alleviate the computation issues of PLMs. PLMs are applied in each group jointly with the candidate news to capture their word-level interaction, and global group-level matching is learned across different groups. In addition, the group-based mechanism could be naturally adapted for long- and short-term user representation learning, in which we build users’ long preferences from the representations of all groups and treat the last group as short interests, respectively. Finally, we employ a gate network to dynamically unify the group-level, long- and short-term representations, yielding comprehensive user-news matching effectively. Extensive experiments are conducted on two real-world datasets. The results show that our proposed method achieves superior performance in news recommendations.

As the basic element of graph-structured data, node has been recognized as the main object of study in graph representation learning. A single node intuitively has multiple node-centered subgraphs from the whole graph (e.g., one person in a social network has multiple social circles based on his different relationships). We study this intuition under the framework of graph contrastive learning, and propose a multiple node-centered subgraphs contrastive representation learning method to learn node representation on graphs in a self-supervised way. Specifically, we carefully design a series of node-centered regional subgraphs of the central node. Then, the mutual information between different subgraphs of the same node is maximized by contrastive loss. Experiments on various real-world datasets and different downstream tasks demonstrate that our model has achieved state-of-the-art results.

Personalized review summarization is a challenging task in recommender systems, which aims to generate condensed and readable summaries for product reviews. Recently, some methods propose to adopt the sentiment signals of reviews to enhance the review summarization. However, most previous works only share the semantic features of reviews via preliminary multi-task learning, while ignoring the rich personalized information of users and products, which is crucial to both sentiment identification and comprehensive review summarization. In this paper, we propose a sentiment-aware review summarization method with an elaborately designed multi-task fine-tuning framework to make full use of personalized information of users and products effectively based on Pretrained Language Models (PLMs). We first denote two types of personalized information including IDs and historical summaries to indicate their identification and semantics information respectively. Subsequently, we propose to incorporate the IDs of the user/product into the PLMs-based encoder to learn the personalized representations of input reviews and their historical summaries in a fine-tuning way. Based on this, an auxiliary context-aware review sentiment classification task and a further sentiment-guided personalized review summarization task are jointly learned. Specifically, the sentiment representation of input review is used to identify relevant historical summaries, which are then treated as additional semantic context features to enhance the summary generation process. Extensive experimental results show our approach could generate sentiment-consistent summaries and outperforms many competitive baselines on both review summarization and sentiment classification tasks.

Anomaly detection in dynamic networks aims to find network elements (e.g., nodes, edges, subgraphs, change points) with significantly different behaviors from the vast majority, it can also devote to community detection and evolution and prediction tasks. Most existing methods focus on one specific task, that is, only detect anomalies of one type of element isolated, so they lose the ability to model the correlation and driving mechanism between different abnormal behavior. Considering that the anomaly detection of one type of element is helpful to other types of elements, i.e., the temporal evolution hidden the dynamic networks are driven by indivisible behavior patterns. So in this paper, we propose a unified Generation model to analyze the dynamic network for Exploring the Abnormal Behaviors of different Scales (GEABS). It can model the relation and catch different levels (node, community and network) of anomaly with a joint statistical network model and detect the community structure and its evolution. Specifically, we denote the parameters of node popularity, community membership to generate the dynamic network with stochastic block model (SBM), we also describe the varying of node and community by dynamic process. With a well-designed generative mechanism, it can detect the change point on network level, temporal evolution on community level and abnormal behavior on node level synchronously, besides, it also detects the community structure effectively. We also propose an effective optimization algorithm with variational inference. Experimental results show that the GEABS achieves better performance on abnormal behavior and community structure compared with baselines.

Exploring the differences and important patterns of nodes from the perspective of roles has gradually developed into an interesting and important topic in network analysis. However, existing role-oriented network embedding methods focus more on identifying underlying roles for static network, which leads to complex temporal behaviors being overlooked and degraded performance facing dynamic network. The few role analytics methods for dynamic networks either cannot learn general node representations or fail to discovery role transitions of nodes. In this work, we propose a unified framework RDNE (Role-oriented Dynamic Network Embedding) to tackle such challenges, which aim to learn multiple embeddings for individual nodes based on time-varying structural behaviors. Based on regular equivalence, RDNE propagates the structural features over the graph to derive the initial role-oriented representations. Then, it applies capsule network to further model the mapping between nodes and roles, which is the first time capsule network is used for role discovery. For the varying and temporal dependence within dynamic network, we utilize the Gated Recurrent Unit to compute historical information and use historical information to influence the generation of representations at the next snapshot. Comprehensive experiments on both synthetic and real-world networks validate the superiority of the proposed RDNE.

Graph neural networks (GNNs) have gained significant success in graph representation learning and become the go-to approach for many graph-based tasks. Despite their effectiveness, the performance of GNNs is known to decline gradually as the number of layers increases. This attenuation is mainly caused by noise propagation, which refers to the useless or negative information propagated (directly or indirectly) from other nodes during the multi-layer graph convolution for node representation learning. This noise increases more severely as the layers of GNNs deepen, which is also a main reason of over-smoothing. In this paper, we propose a new convolution strategy for GNNs to address this problem via suppressing the noise propagation. Specifically, we first find that the feature propagation process of GNNs can be taken as a Markov chain. And then, based on the idea of Markov clustering, we introduce a new graph inflation layer (i.e., using a power function over the distribution) into GNNs to prevent noise propagating from local neighbourhoods to the whole graph with the increase of network layers. Our method is simple in design, which does not require any changes on the original basis and therefore can be easily extended. We conduct extensive experiments on real-world networks and have a stable improved performance as the network depth increases over existing GNNs.

Graph neural network (GNN) has become a popular tool to analyze the graph data. Existing GNNs only focus on networks with first-order dependency, that is, conventional networks following the Markov property. However, many networks in real life own the higher-order dependency, such as click-stream data where the choice of the next page depends not only on the current page but also on previous pages. This kind of sequential data from complex systems (including natural dependencies) are often ignored by existing GNNs which makes them ineffective. To address this problem, we propose for the first time new GNN approaches for higher-order networks in this paper. First, we form sequence fragments by the current node and its predecessor nodes of different orders as candidate higher-order dependencies. When the fragment significantly affects the probability distribution of different successor nodes of the current node, we include it in the higher-order dependency set. We formulize the network with higher-order dependency as an augmented conventional first-order network, and then feed it into GNNs to derive network embeddings. Moreover, we further propose a new end-to-end GNN framework for dealing with higher-order networks directly in the model. Specifically, the higher-order dependency is used as the neighbor aggregation controller when the node is embedded and updated. In the graph convolutional layer, in addition to the first-order neighbor information, we also aggregate the middle node information from the higher-order dependency segment. We finally test the new approaches on three real networks with higher-order dependency, and compare with some state-of-the-art methods. The results show significant improvements of the new approaches which consider higher-order dependency.

In Community Question Answering (CQA) websites, expert finding aims at seeking suitable experts to answer questions. The key is to explore the inherent relevance based on the representations of questions and experts. Existing methods usually learn these features from single view information (e.g., question title), which would be not insufficient to fully learn their representations. In this paper, we propose a personalized expert finding method with a multi-view attentive matching mechanism. We design three modules under the multi-view paradigm, including a question encoder, an intra-view encoder, and an inter-view encoder, which aims to comprehend the comprehensive relationships between experts and questions. In the question encoder, we learn the multi-view question features from its title, body and tag views respectively. In the intra-view encoder, we design an interactive attention network to capture the view-specific relevance between the target question and the historical answered questions of experts for all different views. Furthermore, in the inter-view encoder we employ a personalized attention network to aggregate different view information to learn expert/question representations. In this way, the match of the expert and question could be fully captured from the multi-view information via the intra- and inter-view mechanisms. Experimental results on six datasets demonstrate that the proposed method could achieve better performance than existing state-of-the-art methods.

Roles of nodes are defined as classes of equivalent nodes. Nodes that have similar local connective patterns may share the same role. As a complementary concept of community, role can also help to recognize real-world entities. For example, it can denote identity or function in social networks. Role has been studied over the past decades, and learning role-based network representations is crucial to many downstream tasks. The important step for role-based network embedding method is extracting features to measure structural similarity instead of proximity. Although some methods have been developed to capture role features to learn structural similarities between nodes, they all design these features of fixed types, such as the global, local, and higher-order features. These features can only represent a certain type of structure, and it is very difficult to model the complex relationship between different scale features in the field of role-based network embedding. Therefore, we propose a novel role-oriented network embedding framework based on adversarial learning between higher-order and local features (ARHOL) to generate powerful role-based node representations. The higher-order features are discrete so we leverage the Auto-Encoder on them to obtain continuous representations. Then we apply the GIN on its outputs to aggregate local information. Finally, we consider the GIN as the generator and design an adversarial game between local features and GIN outputs to integrate these two aspects of features, which can enhance each other and improve the robustness. The extensive experiments on real-world networks demonstrate the superiority and efficiency of our model, and prove the effectiveness of integrating higher-order and local features.

Role of node is defined on structural similarity or local connective pattern, describing the functions of node in the network. In real-world situation, it can denote person’s identity and status. It has been studied over the past decades, and learning role-based network representations is crucial to many downstream tasks. In this field, the important step for is extracting some measurements to evaluate structural similarity. Although some methods have been developed to capture the role features to learn the structural similarities between nodes, they all design the features of fixed types, such as global, local, and higher-order features. These features can only discover single type of roles, and simply combing them may cause damage to performance. It is very difficult to model the complex relationship between different scale features in the field of role-based network embedding. Therefore, we propose a novel adversarial framework to generate structural node representations via higher-order features and adversarial learning (SHOAL). We leverage the Auto-Encoder on higher-order features and some GNNs on its outputs to aggregate local neighbors. We believe that higher-order and local features can denote roles, and effectively integrating them will help for role discovery. So we consider the GNNs as the generator and design an adversarial game between these features, which can also improve the robustness. The experiments on real-world networks demonstrate the superiority and efficiency of our model, and the results also prove the effectiveness of integrating higher-order and local features.

Review summarization aims to generate condensed text for online product reviews, and has attracted more and more attention in E-commerce platforms. In addition to the input review, the quality of generated summaries is highly related to the characteristics of users and products, e.g., their historical summaries, which could provide useful clues for the target summary generation. However, most previous works ignore the underlying interaction between the given input review and the corresponding historical summaries. Therefore, we aim to explore how to effectively incorporate the history information into the summary generation. In this paper, we propose a novel transformer-based reasoning framework for personalized review summarization. We design an elaborately adapted transformer network containing an encoder and a decoder, to fully infer the important and informative parts among the historical summaries in terms of the input review to generate more comprehensive summaries. In the encoder of our approach, we develop an inter- and intra-attention to involve the history information selectively to learn the personalized representation of the input review. In the decoder part, we propose to incorporate the constructed reasoning memory learning from historical summaries into the original transformer decoder, and design a memory-decoder attention module to retrieve more useful information for the final summary generation. Extensive experiments are conducted and the results show our approach could generate more reasonable summaries for recommendation, and outperform many competitive baseline methods.

Product reviews can provide rich information about the opinions users have of products. However, it is nontrivial to effectively infer user preference and item characteristics from reviews due to the complicated semantic understanding. Existing methods usually learn features for users and items from reviews in single static fashions and cannot fully capture user preference and item features. In this article, we propose a neural review-based recommendation approach that aims to learn comprehensive representations of users/items under a three-tier attention framework. We design a review encoder to learn review features from words via a word-level attention, an aspect encoder to learn aspect features via a review-level attention, and a user/item encoder to learn the final representations of users/items via an aspect-level attention. In word- and review-level attentions, we adopt the context-aware mechanism to indicate importance of words and reviews dynamically instead of static attention weights. In addition, the attentions in the word and review levels are of multiple paradigms to learn multiple features effectively, which could indicate the diversity of user/item features. Furthermore, we propose a personalized aspect-level attention module in user/item encoder to learn the final comprehensive features. Extensive experiments are conducted and the results in rating prediction validate the effectiveness of our method.

Anomaly detection in multilayer graphs becomes more critical in many application scenarios, i.e., identifying crime hotspots in urban areas by discovering suspicious and illicit behaviors in social networks. However, it is a big challenge to identify anomalies in a layer graph due to the insufficient anomaly features. Most existing methods of anomaly detection determine whether a node is abnormal by looking at the observable anomalous feature values. However, these methods are not suitable for scenarios in which the abnormal features are scarce, e.g., geometric graphs or non-public data in social network services. In this paper, to detect anomaly in a graph with insufficient anomalous features, we propose a pioneering approach ASD-FT (Anomaly Subgraph Detection with Feature Transfer) based on a strategy of anomalous feature transfers between different layers of a multilayer graph. The proposed ASD-FT detects anomaly subgraphs from the graph of the target layer by analyzing the anomalous features in the graph of another layer. We demonstrate the effectiveness and robustness of our approach ASD-FT with extensive experiments on five real-world datasets.

There are two main paradigms to exploit review information for recommendation. One is to concatenate all reviews of a user/item into a long document, which may neglect the different usefulness of reviews. The other paradigm is review-level i.e., analyzing each review separately to learn user/item features. In fact, the two paradigms are complementary, and fusing them together has the potential to learn more comprehensive features of users/items. Hence, we propose a unified framework to jointly learn document- and review-level representations of users/items. We design a document encoder to learn document-level features of users/items. Then, we use a review encoder to learn representations of reviews from words, and a user/item encoder to learn review-level features of users/items. Besides, different reviews from the same user may have different importance for different target items due to different item characteristics. We propose a cross attention model for user representation learning whose query vector is the embedding of target item ID, and apply it to the above three encoders to select different informative words and reviews for different target items. Extensive experiments validate the effectiveness of our method.

Emergency Medical Services (EMS) are of great importance to saving people's lives from emergent accidents and diseases by efficiently picking up patients using ambulances. The transporting capability of an EMS system (e.g., defined as the average pickup time of patients) significantly depends on the real-time redeployment strategy of ambulances. That is, which station should an ambulance be redeployed to, after it becomes available (after it transports a patient to a hospital or after it finishes the in-site treatment for a patient)? However, it is a challenging task concerning with the multiple data D1-D5 as detailed in Introduction. To this end, in this paper, we propose a data-driven real-time ambulance redeployment approach that redeploys an ambulance to a proper station after it becomes available, so as to optimize the transporting capability of an EMS system, considering the aforementioned multiple data D1-D5. Specifically, the proposed approach is comprised of two stages to well consider the D1-D5. First, we propose a method (a safety time-based urgency index) to incorporate D1, D2, and D3 into each ambulance station's urgency degree (D*). Second, we propose an optimal matching algorithm to combine D*, D4, and D5 into the redeployment of the current available ambulance. Experimental results using data collected in real world demonstrate the significant advantages of our approach over many baselines. Comparing with baselines, our approach can save ~4 minutes (~35 percent) of the average pickup time for each patient, improve the ratio of patients picked up within 10 minutes from 0.684 and 0.803 (~17 percent), and largely enhance the survival rate of patients (~12 percent for patients in category A1 and ~17 percent for patients in A2).

Existing review-based recommendation methods usually use the same model to learn the representations of all users/items from reviews posted by users towards items. However, different users have different preference and different items have different characteristics. Thus, the same word or the similar reviews may have different informativeness for different users and items. In this paper we propose a neural recommendation approach with personalized attention to learn personalized representations of users and items from reviews. We use a review encoder to learn representations of reviews from words, and a user/item encoder to learn representations of users or items from reviews. We propose a personalized attention model, and apply it to both review and user/item encoders to select different important words and reviews for different users/items. Experiments on five datasets validate our approach can effectively improve the performance of neural recommendation.

Emergency medical service provides a variety of services for those in need of emergency care. One of the major challenges encountered by emergency service providers is selecting the appropriate locations for ambulance stations. Prior works measure spatial proximity under Euclidean space or static road network. In this paper, we focus on locating the ambulance stations by using the real traffic information so as to minimize the average travel-time to reach the emergency requests. To this end, we estimate the travel-time of road segments using real GPS trajectories and propose an efficient PAM-based refinement for the location problem. We conduct extensive experimental evaluations using real emergency requests collected from Tianjin, and the result shows that the proposed solution can reduce the travel-time to reach the emergency requests by 29.9% when compared to the original locations of ambulance stations.