Retrieval-augmented generation (RAG) is widely adopted for radiology report generation with medical vision-language models, leveraging external reports as linguistic references. However, existing RAG methods rely primarily on dense embedding similarity, which may retrieve reports that are semantically related yet clinically inconsistent with respect to presence or laterality constraints. Such inconsistencies are often propagated into generation, resulting in contradictory or unsupported findings. We propose an evidence-guided retrieval-augmented framework EviRAG that decomposes retrieval into structured and unstructured alignment levels. First, we induce structured clinical triplets from both query and database cases through targeted visual interrogation, projecting images into a shared evidence space. Triplet-level alignment enforces explicit agreement over presence and laterality variables, yielding a clinically admissible candidate set via structural ranking. Within this constrained space, we perform semantic alignment in a shared multimodal embedding space to capture nuanced descriptive correspondence. The top-ranked reports and query image are jointly fed into a medical vision-language model for report generation. Comprehensive experiments on radiology report generation benchmarks show that EviRAG substantially reduces clinical inconsistencies compared to strong medical vision-language baselines. The source code is available at https://github.com/liamgu06/EviRAG.

Graph-level classification involves analyzing the property of the whole graph, which is typically solved by using graph neural networks (GNNs). Existing efforts generally assume a balanced class distribution. However, real-world data often exhibit long-tailed distributions, i.e., tail classes have significantly fewer samples than head classes, and thus directly applying GNNs is eventually biased toward the head classes, resulting in limited generalization over the tail classes. Moreover, the predictions of existing algorithms are usually not trustworthy, and the trained classifiers remain ignorant to their predictive confidence. Towards this end, in this paper we develop a principled framework called GraphEVER for long-tailed graph-level classification. Technically, GraphEVER incorporates the beliefs of multiple experts and leverages the idea of subjective logic within the Dempster-Shafer Evidence Theory (DST). It can provide the evidence and uncertainty estimation for each expert, where the evidence is parameterized by a Dirichlet distribution to model class probability distribution, and the uncertainty is quantified via a well-defined theoretical framework. In this way, diverse experts can be integrated under DST to endow the classifier with both reliability and robustness. Moreover, we propose an evidence-based routing mechanism to dynamically assign experts, such that the tail classes can receive more attention, while the head classes can reduce redundant engaged experts, further cutting down the computational cost and improving the efficiency. Extensive experiments on seven datasets verify the superiority of our proposed framework.

Out-of-Distribution (OOD) detection, which seeks to identify samples deviating from the In-Distribution (ID) training distribution at test time, is crucial for building robust machine learning systems. While extensive efforts have been made for Euclidean data, OOD detection on graph-structured data remains relatively underexplored. On the one hand, the specific properties of a graph may be attributed to its substructures. On the other hand, acquiring labeled data for graph learning is typically time-consuming and labor-intensive. Toward this end, in this paper, we propose a novel kernel-enhanced graph substructure learning framework termed KEGOD for unsupervised graph OOD detection. Specifically, we introduce a learnable graph generator to construct the augmented graph view that preserves distinguishable structure information. Then, for both the input graph and augmented view, a graph neural network (GNN) branch and a graph kernel (GK) branch are incorporated to explore graph latent patterns. By performing multi-branch concordance learning on the extracted graph patterns, our KEGOD captures complementary ID structural semantics in both implicit and explicit manners, enabling reliable detection of OOD graphs through semantic inconsistency. Finally, we build a self-adaptive training mechanism to automatically control diverse sensitivities of the graph patterns. Experimental results on several public graph datasets reveal the superiority of our KEGOD. Our code is available at~ https://github.com/jamesyifan/KEGOD.

Graph neural networks (GNNs) have essentially taken over as the de facto model for learning graph-structured data. However, the majority of existing methods perform transductive learning in a known graph, which is unable to tackle abundant in-the-wild unseen graphs with potential domain shifts. Even worse, these graphs, accompanied by domain shifts on structural topology and node attributes, bring in vulnerable data bias and thus a huge drop in performance. To tackle this, we propose a novel GNN method named spectral optimal transport (SPOT) for effective domain generalization on graphs. Our method is motivated by the fact that the high-frequency graph spectrum is more likely to indicate domain differences. In particular, we formulate the structural augmentation as an optimal transport problem to retain low-frequency key knowledge and solve the problem using Sinkhorn-Knopp algorithm. In addition, we incorporate an adaptive perturbation strategy to deep features, where the direction of the additive noise is determined by the homophily degrees to maintain semantic properties. Accordingly, we meticulously construct a collection of real-world benchmark datasets to assess the domain generalization capability of our model on graphs, and extensive experiments confirm the effectiveness of our proposed SPOT.

Graph domain adaptation has emerged as a critical challenge in real-world applications, where labeled graph data is often scarce and expensive to obtain. While existing methods have shown promise, they typically require access to source domain data, which may be restricted due to privacy concerns or data regulations. To address these limitations, we investigate the challenging yet practical problem of source-free graph domain adaptation. We propose a new approach namedRobust CrossSupervision with Target Mining (ROSE) for this problem. ROSE achieves robustness by considering the complementary topology of graphs. The model consists of a message-passing branch for local semantic learning and a graph-kernel branch for global structural capture. Both branches are incorporated into a unified cross-supervision framework. To improve the robustness of the optimization process, we explore the context of the target domain, and divide the target data into discriminant set and anchor set. Then we incorporate the two tasks into a meta-learning optimization framework. Extensive experiments on benchmark datasets have demonstrated that our ROSE, compared with a wide range of baselines, always yields superior performance. The source code is available athttps://github.com/luo-junyu/ROSE.

Graph retrieval (GR), a ranking procedure that aims to sort the graphs in a database by their relevance to a query graph in decreasing order, has wide applications across diverse domains, such as visual object detection and myreddrug discovery. Existing Graph Retrieval (GR) approaches usually compare graph pairs at a detailed level and generate quadratic similarity scores. In realistic scenarios, conducting quadratic fine-grained comparisons is costly. However, coarse-grained comparisons would result in performance loss. Moreover, label scarcity in real-world data brings extra challenges. To tackle these issues, we investigate a more realistic GR problem, namely, efficient graph retrieval (EGR). Our key intuition is that, since there are numerous underutilized unlabeled pairs in realistic scenarios, by leveraging the additional information they provide, we can achieve speed-up while simplifying the model without sacrificing performance. Following our intuition, we propose an efficient model called Dual-TowerModel withDividing, Contrasting andAlignment (TowerDNA). TowerDNA utilizes a GNN-based dual-tower model as a backbone to quickly compare graph pairs in a coarse-grained manner. In addition, to effectively utilize unlabeled pairs, TowerDNA first identifies confident pairs from unlabeled pairs to expand labeled datasets. It then learns from remaining unconfident pairs via graph contrastive learning with geometric correspondence. To integrate all semantics with reduced biases, TowerDNA generates prototypes using labeled pairs, which are aligned within both confident and unconfident pairs. Extensive experiments on diverse realistic datasets demonstrate that TowerDNA achieves comparable performance to fine-grained methods while providing a 10× speed-up.

This paper investigates the problem of learning mesh-based physical simulations, which is a crucial task with applications in fluid mechanics and aerodynamics. Recent works typically utilize graph neural networks (GNNs) to produce next-time states on irregular meshes by modeling interacting dynamics, and then adopt iterative rollouts for the whole trajectories. However, these methods cannot achieve satisfactory performance in long-term predictions due to the failure of capturing long-term dependency and potential error accumulations. To tackle this, we introduce a new future-to-present learning perspective, and further develop a simple yet effective approach named Foresight And Interpolation (FAIR) for long-term mesh-based simulations. The main idea of our FAIR is to first learn a graph ODE model for coarse long-term predictions and then refine short-term predictions via interpolation. Specifically, FAIR employs a continuous graph ODE model that incorporates past states into the evolution of interacting node representations, which is capable of learning coarse long-term trajectories under a multi-task learning framework. Then, we leverage a channel aggregation strategy to summarize the trajectories for refined short-term predictions, which can be illustrated using an interpolation process. Through pyramid-like alternative propagation between the foresight step and refinement step, our proposed framework FAIR can generate accurate long-term trajectories, achieving a significant error reduction compared with the best baseline on four benchmark datasets. Extensive ablation studies and visualization further validate the superiority of our proposed FAIR.

Graph neural networks (GNNs) have shown remarkable success in graph-level classification tasks. However, most of the existing GNN-based studies are based on balanced datasets, while many real-world datasets exhibit long-tailed distributions. In such datasets, the tail classes receive limited attention during training, leading to prediction bias and degraded performance. To address this issue, a range of long-tailed learning strategies have been proposed, such as data re-balancing and transfer learning. However, these approaches encounter several challenges, including insufficient representation capacity for tail classes and their evaluation solely on uniform test data, limiting their capacity to handle unknown class distributions. To tackle these challenges, we introduce a novel framework, namely Knowledge-diverse Experts (KDEX) for long-tailed graph classification. Our KDEX leverages a dynamic memory module to enable the transfer of knowledge from head to tail, which improves the representation ability of the tail. To deal with unknown test distributions, KDEX introduces a knowledge-diverse expert training approach to train experts with different capacities in managing various test distributions. Moreover, we train the hierarchical router in a self-supervised manner to dynamically aggregate each knowledge-diverse expert during testing. Experimental results on multiple benchmarks reveal that our KDEX outperforms current baselines in both standard and test-agnostic long-tailed graph classification.

Collaborative Filtering (CF) is a pivotal research area in recommender systems that capitalizes on collaborative similarities between users and items to provide personalized recommendations. With the remarkable achievements of node embedding-based Graph Neural Networks (GNNs), we explore the upper bounds of expressiveness inherent to embedding-based methodologies and tackle the challenges by reframing the CF task as a graph-signal processing problem. To this end, we propose PolyCF, a flexible graph signal filter that leverages polynomial graph filters to process interaction signals. PolyCF exhibits the capability to capture spectral features across multiple eigenspaces through a series of Generalized Gram filters and is able to approximate the optimal polynomial response function for recovering missing interactions. A graph optimization objective and a pairwise ranking objective are jointly used to optimize the parameters of the convolution kernel. Experiments on three widely adopted datasets demonstrate the superiority of PolyCF over the state-of-the-art CF methods.

The recently developed unsupervised graph representation learning approaches apply contrastive learning into graph-structured data and achieve promising performance. However, these methods mainly focus on graph augmentation for positive samples, while the negative mining strategies for graph contrastive learning are less explored, leading to sub-optimal performance. To tackle this issue, we propose a Graph Adversarial Contrastive Learning (GraphACL) scheme that learns a bank of negative samples for effective self-supervised whole-graph representation learning. Our GraphACL consists of (i) a graph encoding branch that generates the representations of positive samples and (ii) an adversarial generation branch that produces a bank of negative samples. To generate more powerful hard negative samples, our method minimizes the contrastive loss during encoding updating while maximizing the contrastive loss adversarially over the negative samples for providing the challenging contrastive task. Moreover, the quality of representations produced by the adversarial generation branch is enhanced through the regularization of carefully designed bank divergence loss and bank orthogonality loss. We optimize the parameters of the graph encoding branch and adversarial generation branch alternately. Extensive experiments on 14 real-world benchmarks on both graph classification and transfer learning tasks demonstrate the effectiveness of the proposed approach over existing graph self-supervised representation learning methods.

Recent years have witnessed the explosive growth of interaction behaviors in multimedia information systems, where multi-behavior recommender systems have received increasing attention by leveraging data from various auxiliary behaviors such as tip and collect. Among various multi-behavior recommendation methods, non-sampling methods have shown superiority over negative sampling methods. However, two observations are usually ignored in existing state-of-the-art non-sampling methods based on binary regression: (1) users have different preference strengths for different items, so they cannot be measured simply by binary implicit data; (2) the dependency across multiple behaviors varies for different users and items. To tackle the above issue, we propose a novel non-sampling learning framework namedCriterion-guidedHeterogeneousCollaborativeFiltering (CHCF). CHCF introduces both upper and lower thresholds to indicate selection criteria, which will guide user preference learning. Besides, CHCF integrates criterion learning and user preference learning into a unified framework, which can be trained jointly for the interaction prediction of the target behavior. We further theoretically demonstrate that the optimization of Collaborative Metric Learning can be approximately achieved by the CHCF learning framework in a non-sampling form effectively. Extensive experiments on three real-world datasets show the effectiveness of CHCF in heterogeneous scenarios.

Graph neural networks have pushed state-of-the-arts in graph classifications recently. Typically, these methods are studied within the context of supervised end-to-end training, which necessities copious task-specific labels. However, in real-world circumstances, labeled data could be limited, and there could be a massive corpus of unlabeled data, even from unknown classes as a complementary. Towards this end, we study the problem of semi-supervised universal graph classification, which not only identifies graph samples which do not belong to known classes, but also classifies the remaining samples into their respective classes. This problem is challenging due to a severe lack of labels and potential class shifts. In this paper, we propose a novel graph neural network framework named UGNN, which makes the best of unlabeled data from the subgraph perspective. To tackle class shifts, we estimate the certainty of unlabeled graphs using multiple subgraphs, which facilities the discovery of unlabeled data from unknown categories. Moreover, we construct semantic prototypes in the embedding space for both known and unknown categories and utilize posterior prototype assignments inferred from the Sinkhorn-Knopp algorithm to learn from abundant unlabeled graphs across different subgraph views. Extensive experiments on six datasets verify the effectiveness of UGNN in different settings.

Sequential recommendation aims at understanding user preference by capturing successive behavior correlations, which are usually represented as the item purchasing sequences based on their past interactions. Existing efforts generally predict the next item via modeling the sequential patterns. Despite effectiveness, there exist two natural deficiencies: (i) user preference is dynamic in nature, and the evolution of collaborative signals is often ignored; and (ii) the observed interactions are often irregularly-sampled, while existing methods model item transitions assuming uniform intervals. Thus, how to effectively model and predict the underlying dynamics for user preference becomes a critical research problem. To tackle the above challenges, in this paper, we focus on continuous-time sequential recommendation and propose a principled graph ordinary differential equation framework named GDERec. Technically, GDERec is characterized by an autoregressive graph ordinary differential equation consisting of two components, which are parameterized by two tailored graph neural networks (GNNs) respectively to capture user preference from the perspective of hybrid dynamical systems. On the one hand, we introduce a novel ordinary differential equation based GNN to implicitly model the temporal evolution of the user-item interaction graph. On the other hand, an attention-based GNN is proposed to explicitly incorporate collaborative attention to interaction signals when the interaction graph evolves over time. The two customized GNNs are trained alternately in an autoregressive manner to track the evolution of the underlying system from irregular observations, and thus learn effective representations of users and items beneficial to the sequential recommendation. Extensive experiments on five benchmark datasets demonstrate the superiority of our model over various state-of-the-art recommendation methods

Next Point-of-Interest (POI) recommendation is a critical task in location-based services that aim to provide personalized suggestions for the user’s next destination. Previous works on POI recommendation have laid focus on modeling the user’s spatial preference. However, existing works that leverage spatial information are only based on the aggregation of users’ previous visited positions, which discourages the model from recommending POIs in novel areas. This trait of position-based methods will harm the model’s performance in many situations. Additionally, incorporating sequential information into the user’s spatial preference remains a challenge. In this article, we propose Diff-POI : a Diffu sion-based model that samples the user’s spatial preference for the next POI recommendation. Inspired by the wide application of diffusion algorithm in sampling from distributions, Diff-POI encodes the user’s visiting sequence and spatial character with two tailor-designed graph encoding modules, followed by a diffusion-based sampling strategy to explore the user’s spatial visiting trends. We leverage the diffusion process and its reverse form to sample from the posterior distribution and optimized the corresponding score function. We design a joint training and inference framework to optimize and evaluate the proposed Diff-POI. Extensive experiments on four real-world POI recommendation datasets demonstrate the superiority of our Diff-POI over state-of-the-art baseline methods. Further ablation and parameter studies on Diff-POI reveal the functionality and effectiveness of the proposed diffusion-based sampling strategy for addressing the limitations of existing methods.

This paper studies the problem of traffic flow forecasting, which aims to predict future traffic conditions on the basis of road networks and traffic conditions in the past. The problem is typically solved by modeling complex spatio-temporal correlations in traffic data using spatio-temporal graph neural networks (GNNs). However, the performance of these methods is still far from satisfactory since GNNs usually have limited representation capacity when it comes to complex traffic networks. Graphs, by nature, fall short in capturing non-pairwise relations. Even worse, existing methods follow the paradigm of message passing that aggregates neighborhood information linearly, which fails to capture complicated spatio-temporal high-order interactions. To tackle these issues, in this paper, we propose a novel model named Dynamic Hypergraph Structure Learning (DyHSL) for traffic flow prediction. To learn non-pairwise relationships, our DyHSL extracts hypergraph structural information to model dynamics in the traffic networks, and updates each node representation by aggregating messages from its associated hyperedges. Additionally, to capture high-order spatio-temporal relations in the road network, we introduce an interactive graph convolution block, which further models the neighborhood interaction for each node. Finally, we integrate these two views into a holistic multi-scale correlation extraction module, which conducts temporal pooling with different scales to model different temporal patterns. Extensive experiments on four popular traffic benchmark datasets demonstrate the effectiveness of our proposed DyHSL compared with a broad range of competing baselines.

Point-of-Interest (POI) recommendation plays a vital role in various location-aware services. It has been observed that POI recommendation is driven by both sequential and geographical influences. However, since there is no annotated label of the dominant influence during recommendation, existing methods tend to entangle these two influences, which may lead to sub-optimal recommendation performance and poor interpretability. In this paper, we address the above challenge by proposing DisenPOI, a novel Disentangled dual-graph framework for POI recommendation, which jointly utilizes sequential and geographical relationships on two separate graphs and disentangles the two influences with self-supervision. The key novelty of our model compared with existing approaches is to extract disentangled representations of both sequential and geographical influences with contrastive learning. To be specific, we construct a geographical graph and a sequential graph based on the check-in sequence of a user. We tailor their propagation schemes to become sequence-/geo-aware to better capture the corresponding influences. Preference proxies are extracted from check-in sequence as pseudo labels for the two influences, which supervise the disentanglement via a contrastive loss. Extensive experiments on three datasets demonstrate the superiority of the proposed model.

In this paper, we study semi-supervised graph classification, a fundamental problem in data mining and machine learning. The problem is typically solved by learning graph neural networks with pseudo-labeling or knowledge distillation to incorporate both labeled and unlabeled graphs. However, these methods usually either suffer from overconfident and biased pseudo-labels or suboptimal distillation caused by the insufficient use of unlabeled data. Inspired by the recent progress of contrastive learning and dual learning, we propose DualGraph, a principled framework to leverage unlabeled graphs more effectively for semi-supervised graph classification. DualGraph consists of a prediction module and a retrieval module to model graphs$G$and their labels$y$from opposite while complementary views (i.e., p(y | G) and p(G | y) respectively). The two modules are jointly trained via posterior regularization, which encourages their inter-module consistency on unlabeled graphs. Moreover, we improve model training for each module with a contrastive learning framework to encourage the intra-module consistency on unlabeled data. Experimental results on a range of publicly accessible datasets reveal the effectiveness of our DualGraph.

Point-of-Interest (POI) recommendation, which benefits from the proliferation of GPS-enabled devices and location-based social networks (LBSNs), plays an increasingly important role in recommender systems. It aims to provide users with the convenience to discover their interested places to visit based on previous visits and current status. Most existing methods usually merely leverage recurrent neural networks (RNNs) to explore sequential influences for recommendation. Despite the effectiveness, these methods not only neglect topological geographical influences among POIs, but also fail to model high-order sequential substructures. To tackle the above issues, we propose a Kernel-Based Graph Neural Network (KBGNN) for next POI recommendation, which combines the characteristics of both geographical and sequential influences in a collaborative way. KBGNN consists of a geographical module and a sequential module. On the one hand, we construct a geographical graph and leverage a message passing neural network to capture the topological geographical influences. On the other hand, we explore high-order sequential substructures in the user-aware sequential graph using a graph kernel neural network to capture user preferences. Finally, a consistency learning framework is introduced to jointly incorporate geographical and sequential information extracted from two separate graphs. In this way, the two modules effectively exchange knowledge to mutually enhance each other. Extensive experiments conducted on two real-world LBSN datasets demonstrate the superior performance of our proposed method over the state-of-the-arts. Our codes are available at https://github.com/ ang6ang/KBGNN.

Click-through rate (CTR) prediction plays a critical role in recommender systems and other applications. Recently, modeling user behavior sequences attracts much attention and brings great improvements in the CTR field. Many existing works utilize attention mechanism or recurrent neural networks to exploit user interest from the sequence, but fail to recognize the simple truth that a user's real-time interests are inherently diverse and fluid. In this paper, we propose DisenCTR, a novel dynamic graph-based disentangled representation framework for CTR prediction. The key novelty of our method compared with existing approaches is to model evolving diverse interests of users. Specifically, we construct a time-evolving user-item interaction graph induced by historical interactions. And based on the rich dynamics supplied by the graph, we propose a disentangled graph representation module to extract diverse user interests. We further exploit the fluidity of user interests and model the temporal effect of historical behaviors using Mixture of Hawkes Process. Extensive experiments on three real-world datasets demonstrate the superior performance of our method comparing to state-of-the-art approaches.

This paper studies semi-supervised graph classification, which is an important problem with various applications in social network analysis and bioinformatics. This problem is typically solved by using graph neural networks (GNNs), which yet rely on a large number of labeled graphs for training and are unable to leverage unlabeled graphs. We address the limitations by proposing the Kernel-based Graph Neural Network (KGNN). A KGNN consists of a GNN-based network as well as a kernel-based network parameterized by a memory network. The GNN-based network performs classification through learning graph representations to implicitly capture the similarity between query graphs and labeled graphs, while the kernel-based network uses graph kernels to explicitly compare each query graph with all the labeled graphs stored in a memory for prediction. The two networks are motivated from complementary perspectives, and thus combing them allows KGNN to use labeled graphs more effectively. We jointly train the two networks by maximizing their agreement on unlabeled graphs via posterior regularization, so that the unlabeled graphs serve as a bridge to let both networks mutually enhance each other. Experiments on a range of well-known benchmark datasets demonstrate that KGNN achieves impressive performance over competitive baselines.

Heterogeneous information network has been widely used to alleviate sparsity and cold start problems in recommender systems since it can model rich context information in user-item interactions. Graph neural network is able to encode this rich context information through propagation on the graph. However, existing heterogeneous graph neural networks neglect entanglement of the latent factors stemming from different aspects. Moreover, meta paths in existing approaches are simplified as connecting paths or side information between node pairs, overlooking the rich semantic information in the paths. In this paper, we propose a novel disentangled heterogeneous graph attention network DisenHAN for top-N recommendation, which learns disentangled user/item representations from different aspects in a heterogeneous information network. In particular, we use meta relations to decompose high-order connectivity between node pairs and propose a disentangled embedding propagation layer which can iteratively identify the major aspect of meta relations. Our model aggregates corresponding aspect features from each meta relation for the target user/item. With different layers of embedding propagation, DisenHAN is able to explicitly capture the collaborative filtering effect semantically. Extensive experiments on three real-world datasets show that DisenHAN consistently outperforms state-of-the-art approaches. We further demonstrate the effectiveness and interpretability of the learned disentangled representations via insightful case studies and visualization.

Click-through rate (CTR) prediction, which aims to predict the probability of a user clicking on an ad or an item, is critical to many online applications such as online advertising and recommender systems. The problem is very challenging since (1) the input features (e.g., the user id, user age, item id, item category) are usually sparse and high-dimensional, and (2) an effective prediction relies on high-order combinatorial features (a.k.a. cross features), which are very time-consuming to hand-craft by domain experts and are impossible to be enumerated. Therefore, there have been efforts in finding low-dimensional representations of the sparse and high-dimensional raw features and their meaningful combinations. In this paper, we propose an effective and efficient method called the AutoInt to automatically learn the high-order feature interactions of input features. Our proposed algorithm is very general, which can be applied to both numerical and categorical input features. Specifically, we map both the numerical and categorical features into the same low-dimensional space. Afterwards, a multi-head self-attentive neural network with residual connections is proposed to explicitly model the feature interactions in the low-dimensional space. With different layers of the multi-head self-attentive neural networks, different orders of feature combinations of input features can be modeled. The whole model can be efficiently fit on large-scale raw data in an end-to-end fashion. Experimental results on four real-world datasets show that our proposed approach not only outperforms existing state-of-the-art approaches for prediction but also offers good explainability. Code is available at: \urlhttps://github.com/DeepGraphLearning/RecommenderSystems.

Online communities such as Facebook and Twitter are enormously popular and have become an essential part of the daily life of many of their users. Through these platforms, users can discover and create information that others will then consume. In that context, recommending relevant information to users becomes critical for viability. However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends. Moreover, the influencers may be context-dependent. That is, different friends may be relied upon for different topics. Modeling both signals is therefore essential for recommendations. We propose a recommender system for online communities based on a dynamic-graph-attention neural network. We model dynamic user behaviors with a recurrent neural network, and context-dependent social influence with a graph-attention neural network, which dynamically infers the influencers based on users' current interests. The whole model can be efficiently fit on large-scale data. Experimental results on several real-world data sets demonstrate the effectiveness of our proposed approach over several competitive baselines including state-of-the-art models.

The proliferation of fake news on social media has opened up new directions of research for timely identification and containment of fake news and mitigation of its widespread impact on public opinion. While much of the earlier research was focused on identification of fake news based on its contents or by exploiting users’ engagements with the news on social media, there has been a rising interest in proactive intervention strategies to counter the spread of misinformation and its impact on society. In this survey, we describe the modern-day problem of fake news and, in particular, highlight the technical challenges associated with it. We discuss existing methods and techniques applicable to both identification and mitigation, with a focus on the significant advances in each method and their advantages and limitations. In addition, research has often been limited by the quality of existing datasets and their specific application contexts. To alleviate this problem, we comprehensively compile and summarize characteristic features of available datasets. Furthermore, we outline new directions of research to facilitate future development of effective and interdisciplinary solutions.

Learning distributed node representations in networks has been attracting increasing attention recently due to its effectiveness in a variety of applications. Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network. However, in reality there usually exists multiple types of proximities between nodes, yielding networks with multiple views. This paper studies learning node representations for networks with multiple views, which aims to infer robust node representations across different views. We propose a multi-view representation learning approach, which promotes the collaboration of different views and lets them vote for the robust representations. During the voting process, an attention mechanism is introduced, which enables each node to focus on the most informative views. Experimental results on real-world networks show that the proposed approach outperforms existing state-of-the-art approaches for network representation learning with a single view and other competitive approaches with multiple views.

Measuring network similarity is a fundamental data mining problem. The mainstream similarity measures mainly leverage the structural information regarding to the entities in the network without considering the network semantics. In the real world, the heterogeneous information networks (HINs) with rich semantics are ubiquitous. However, the existing network similarity doesn't generalize well in HINs because they fail to capture the HIN semantics. The meta-path has been proposed and demonstrated as a right way to represent semantics in HINs. Therefore, original meta-path based similarities (e.g., PathSim and KnowSim) have been successful in computing the entity proximity in HINs. The intuition is that the more instances of meta-path(s) between entities, the more similar the entities are. Thus the original meta-path similarity only applies to computing the proximity of two neighborhood (connected) entities. In this paper, we propose the distant meta-path similarity that is able to capture HIN semantics between two distant (isolated) entities to provide more meaningful entity proximity. The main idea is that even there is no shared neighborhood entities of (i.e., no meta-path instances connecting) the two entities, but if the more similar neighborhood entities of the entities are, the more similar the two entities should be. We then find out the optimum distant meta-path similarity by exploring the similarity hypothesis space based on different theoretical foundations. We show the state-of-the-art similarity performance of distant meta-path similarity on two text-based HINs and make the datasets public available.

Recent studies have demonstrated the power of modeling real world data as heterogeneous information networks (HINs) consisting of multiple types of entities and relations. Unfortunately, most of such studies (e.g., similarity search) confine discussions on the networks with only a few entity and relationship types, such as DBLP. In the real world, however, the network schema can be rather complex, such as Freebase. In such HINs with rich schema, it is often too much burden to ask users to provide explicit guidance in selecting relations for similarity search. In this paper, we study the problem of relation similarity search in schema-rich HINs. Under our problem setting, users are only asked to provide some simple relation instance examples (e.g., 〈Barack Obama, John Kerry〉 and 〈George W. Bush, Condoleezza Rice〉) as a query, and we automatically detect the latent semantic relation (LSR) implied by the query (e.g., “president vs. secretary-of-state”). Such LSR will help to find other similar relation instances (e.g., 〈Bill Clinton, Madeleine Albright〉). In order to solve the problem, we first define a new meta-path-based relation similarity measure, RelSim, to measure the similarity between relation instances in schema-rich HINs. Then given a query, we propose an optimization model to efficiently learn LSR implied in the query through linear programming, and perform fast relation similarity search using RelSim based on the learned LSR. The experiments on real world datasets derived from Freebase demonstrate the effectiveness and efficiency of our approach.

We study the problem of visualizing large-scale and high-dimensional data in a low-dimensional (typically 2D or 3D) space. Much success has been reported recently by techniques that first compute a similarity structure of the data points and then project them into a low-dimensional space with the structure preserved. These two steps suffer from considerable computational costs, preventing the state-of-the-art methods such as the t-SNE from scaling to large-scale and high-dimensional data (e.g., millions of data points and hundreds of dimensions). We propose the LargeVis, a technique that first constructs an accurately approximated K-nearest neighbor graph from the data and then layouts the graph in the low-dimensional space. Comparing to t-SNE, LargeVis significantly reduces the computational cost of the graph construction step and employs a principled probabilistic model for the visualization step, the objective of which can be effectively optimized through asynchronous stochastic gradient descent with a linear time complexity. The whole procedure thus easily scales to millions of high-dimensional data points. Experimental results on real-world data sets demonstrate that the LargeVis outperforms the state-of-the-art methods in both efficiency and effectiveness. The hyper-parameters of LargeVis are also much more stable over different data sets.

One of the key obstacles in making learning protocols realistic in applications is the need to supervise them, a costly process that often requires hiring domain experts. We consider the framework to use the world knowledge as indirect supervision. World knowledge is general-purpose knowledge, which is not designed for any specific domain. Then, the key challenges are how to adapt the world knowledge to domains and how to represent it for learning. In this article, we provide an example of using world knowledge for domain-dependent document clustering. We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network. Then, we propose a clustering algorithm that can cluster multiple types and incorporate the sub-type information as constraints. In the experiments, we use two existing knowledge bases as our sources of world knowledge. One is Freebase, which is collaboratively collected knowledge about entities and their organizations. The other is YAGO2, a knowledge base automatically extracted from Wikipedia and maps knowledge to the linguistic knowledge base, WordNet. Experimental results on two text benchmark datasets (20newsgroups and RCV1) show that incorporating world knowledge as indirect supervision can significantly outperform the state-of-the-art clustering algorithms as well as clustering algorithms enhanced with world knowledge features. A preliminary version of this work appeared in the proceedings of KDD 2015 [Wang et al. 2015a]. This journal version has made several major improvements. First, we have proposed a new and general learning framework for machine learning with world knowledge as indirect supervision, where document clustering is a special case in the original paper. Second, in order to make our unsupervised semantic parsing method more understandable, we add several real cases from the original sentences to the resulting logic forms with all the necessary information. Third, we add details of the three semantic filtering methods and conduct deep analysis of the three semantic filters, by using case studies to show why the conceptualization-based semantic filter can produce more accurate indirect supervision. Finally, in addition to the experiment on 20 newsgroup data and Freebase, we have extended the experiments on clustering results by using all the combinations of text (20 newsgroup, MCAT, CCAT, ECAT) and world knowledge sources (Freebase, YAGO2).

As a fundamental task, document similarity measure has broad impact to document-based classification, clustering and ranking. Traditional approaches represent documents as bag-of-words and compute document similarities using measures like cosine, Jaccard, and dice. However, entity phrases rather than single words in documents can be critical for evaluating document relatedness. Moreover, types of entities and links between entities/words are also informative. We propose a method to represent a document as a typed heterogeneous information network (HIN), where the entities and relations are annotated with types. Multiple documents can be linked by the words and entities in the HIN. Consequently, we convert the document similarity problem to a graph distance problem. Intuitively, there could be multiple paths between a pair of documents. We propose to use the meta-path defined in HIN to compute distance between documents. Instead of burdening user to define meaningful meta-paths, an automatic method is proposed to rank the meta-paths. Given the meta-paths associated with ranking scores, an HIN-based similarity measure, KnowSim, is proposed to compute document similarities. Using Freebase, a well-known world knowledge base, to conduct semantic parsing and construct HIN for documents, our experiments on 20Newsgroups and RCV1 datasets show that KnowSim generates impressive high-quality document clustering.

One of the key obstacles in making learning protocols realistic in applications is the need to supervise them, a costly process that often requires hiring domain experts. We consider the framework to use the world knowledge as indirect supervision. World knowledge is general-purpose knowledge, which is not designed for any specific domain. Then the key challenges are how to adapt the world knowledge to domains and how to represent it for learning. In this paper, we provide an example of using world knowledge for domain dependent document clustering. We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network. Then we propose a clustering algorithm that can cluster multiple types and incorporate the sub-type information as constraints. In the experiments, we use two existing knowledge bases as our sources of world knowledge. One is Freebase, which is collaboratively collected knowledge about entities and their organizations. The other is YAGO2, a knowledge base automatically extracted from Wikipedia and maps knowledge to the linguistic knowledge base, Word-Net. Experimental results on two text benchmark datasets (20newsgroups and RCV1) show that incorporating world knowledge as indirect supervision can significantly outperform the state-of-the-art clustering algorithms as well as clustering algorithms enhanced with world knowledge features.

This paper studies the problem of embedding very large information networks into low-dimensional vector spaces, which is useful in many tasks such as visualization, node classification, and link prediction. Most existing graph embedding methods do not scale for real world information networks which usually contain millions of nodes. In this paper, we propose a novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted. The method optimizes a carefully designed objective function that preserves both the local and global network structures. An edge-sampling algorithm is proposed that addresses the limitation of the classical stochastic gradient descent and improves both the effectiveness and the efficiency of the inference. Empirical experiments prove the effectiveness of the LINE on a variety of real-world information networks, including language networks, social networks, and citation networks. The algorithm is very efficient, which is able to learn the embedding of a network with millions of vertices and billions of edges in a few hours on a typical single machine. The source code of the LINE is available online\footnote{\url{https://github.com/tangjianpku/LINE}}.

Many problems in natural language processing, data mining, information retrieval, and bioinformatics can be formalized as string transformation, which is a task as follows. Given an input string, the system generates the k most likely output strings corresponding to the input string. This paper proposes a novel and probabilistic approach to string transformation, which is both accurate and efficient. The approach includes the use of a log linear model, a method for training the model, and an algorithm for generating the top k candidates, whether there is or is not a predefined dictionary. The log linear model is defined as a conditional probability distribution of an output string and a rule set for the transformation conditioned on an input string. The learning method employs maximum likelihood estimation for parameter estimation. The string generation algorithm based on pruning is guaranteed to generate the optimal top k candidates. The proposed method is applied to correction of spelling errors in queries as well as reformulation of queries in web search. Experimental results on large scale data show that the proposed approach is very accurate and efficient improving upon existing methods in terms of accuracy and efficiency in different settings.

New challenges have been presented to classical topic models when applied to social media, as user-generated content suffers from significant problems of data sparseness. A variety of heuristic adjustments to these models have been proposed, many of which are based on the use of context information to improve the performance of topic modeling. Existing contextualized topic models rely on arbitrary manipulation of the model structure, by incorporating various context variables into the generative process of classical topic models in an ad hoc manner. Such manipulations usually result in much more complicated model structures, sophisticated inference procedures, and low generalizability to accommodate arbitrary types or combinations of contexts. In this paper we explore a different direction. We propose a general solution that is able to exploit multiple types of contexts without arbitrary manipulation of the structure of classical topic models. We formulate different types of contexts as multiple views of the partition of the corpus. A co-regularization framework is proposed to let these views collaborate with each other, vote for the consensus topics, and distinguish them from view-specific topics. Experiments with real-world datasets prove that the proposed method is both effective and flexible to handle arbitrary types of contexts.

Researchers and social observers have both believed that hashtags, as a new type of organizational objects of information, play a dual role in online microblogging communities (e.g., Twitter). On one hand, a hashtag serves as a bookmark of content, which links tweets with similar topics; on the other hand, a hashtag serves as the symbol of a community membership, which bridges a virtual community of users. Are the real users aware of this dual role of hashtags? Is the dual role affecting their behavior of adopting a hashtag? Is hashtag adoption predictable? We take the initiative to investigate and quantify the effects of the dual role on hashtag adoption. We propose comprehensive measures to quantify the major factors of how a user selects content tags as well as joins communities. Experiments using large scale Twitter datasets prove the effectiveness of the dual role, where both the content measures and the community measures significantly correlate to hashtag adoption on Twitter. With these measures as features, a machine learning model can effectively predict the future adoption of hashtags that a user has never used before.

To optimize the performance of web crawlers, various page importance measures have been studied to select and order URLs in crawling. Most sophisticated measures (e.g. breadth-first and PageRank) are based on link structure. In this paper, we treat the problem from another perspective and propose to measure page importance through mining user interest and behaviors from web browse logs. Unlike most existing approaches which work on single URL, in this paper, both the log mining and the crawl ordering are performed at the granularity of URL pattern. The proposed URL pattern-based crawl orderings are capable to properly predict the importance of newly created (unseen) URLs. Promising experimental results proved the feasibility of our approach.

Behavioral targeting (BT), which aims to sell advertisers those behaviorally related user segments to deliver their advertisements, is facing a bottleneck in serving the rapid growth of long tail advertisers. Due to the small business nature of the tail advertisers, they generally expect to accurately reach a small group of audience, which is hard to be satisfied by classical BT solutions with large size user segments. In this paper, we propose a novel probabilistic generative model named Rank Latent Dirichlet Allocation (RANKLDA) to rank audience according to their ads click probabilities for the long tail advertisers to deliver their ads. Based on the basic assumption that users who clicked the same group of ads will have a higher probability of sharing similar latent search topical interests, RANKLDA combines topic discovery from users' search behaviors and learning to rank users from their ads click behaviors together. In computation, the topic learning could be enhanced by the supervised information of the rank learning and simultaneously, the rank learning could be better optimized by considering the discovered topics as features. This co-optimization scheme enhances each other iteratively. Experiments over the real click-through log of display ads in a public ad network show that the proposed RANKLDA model can effectively rank the audience for the tail advertisers.

Twitter is one of the biggest platforms where massive instant messages (i.e. tweets) are published every day. Users tend to express their real feelings freely in Twitter, which makes it an ideal source for capturing the opinions towards various interesting topics, such as brands, products or celebrities, etc. Naturally, people may anticipate an approach to receiving the common sentiment tendency towards these topics directly rather than through reading the huge amount of tweets about them. On the other side, Hashtags, starting with a symbol "#" ahead of keywords or phrases, are widely used in tweets as coarse-grained topics. In this paper, instead of presenting the sentiment polarity of each tweet relevant to the topic, we focus our study on hashtag-level sentiment classification. This task aims to automatically generate the overall sentiment polarity for a given hashtag in a certain time period, which markedly differs from the conventional sentence-level and document-level sentiment analysis. Our investigation illustrates that three types of information is useful to address the task, including (1) sentiment polarity of tweets containing the hashtag; (2) hashtags co-occurrence relationship and (3) the literal meaning of hashtags. Consequently, in order to incorporate the first two types of information into a classification framework where hashtags can be classified collectively, we propose a novel graph model and investigate three approximate collective classification algorithms for inference. Going one step further, we show that the performance can be remarkably improved using an enhanced boosting classification setting in which we employ the literal meaning of hashtags as semi-supervised information. Experimental results on a real-life data set consisting of 29,195 tweets and 2,181 hashtags show the effectiveness of the proposed model and algorithms.

With the rapid growth of web 2.0, online product reviews generated by users are becoming increasingly useful for customers to make purchase decisions. In this paper, we focus on the problem of classifying user reviews as recommended the product or not. The proposed method first mines the product features and relevant opinions, and then determines the overall sentiment orientation of the review based on the polarity and strength of these opinions. The evaluation results show the effectiveness of our proposed method in product feature mining and review classification.

With the rapid growth of web data, people sometime need semantic similar information in order to obtain a clear outline of their interests, so recommendation is needed to provide relevant information to users' queries. In this paper, we propose a method to recommend semantic similar movies and stars to users' queries, styles and stories. The system measures the similarities between movies according to genre and style features extracted from YAGO and IMDB. Experimental results show that the recommendations meet users' interests.

Recommender systems have emerged as an essential response to the rapidly growing digital information phenomenon in which users are finding it more and more difficult to locate the right information at the right time. Systems under Web2.0 allow users not only to give resources- ratings but also to assign tags to them. Tags play a significant role in Web 2.0. They can be used for navigation, browsing, recommendation and so on. In this paper, we propose a novel recommendation algorithm, which is based on social networks. The social network is established among users and items, taking into account both the information of ratings and tags. We consider users' co-tagging behaviors and add the similarity relationship to the graph to enhance the performance. Our algorithm is based on the Random Walk with Restarts but provides a more natural and efficient way to represent social networks. Having considered the influence of tags, the transition matrix is denser and the recommendation is more accurate. By evaluating our new algorithm and comparing it to the baseline algorithm which is used in many real world recommender systems on a real life dataset, we make the conclusion that our method performs better than the baseline method.

Computing top-k results matching XML queries is gaining importance due to the increasing of large XML repositories. In this paper, we propose a novel two-layer-based index construction and associated algorithms for efficiently computing top-k results for SLCA-based XML keyword search. We have conducted expensive experiments and the results show great advantage on efficiency compared with existing approaches.

Web pages are typical semi-structure data. Some tree-based models have been proposed to describe the semantic content structure of web pages in order to facilitate further content analysis. However, most existing models only present the segmentation hierarchy of content blocks rather than the semantic relationships among them. In this work, we propose a novel web page semantic structure model, called Logical Structure Model. It can present more comprehensive structure information of web pages. Based on this model, the hidden patterns in web content can be revealed easier. The proposed model has been used to facilitate identifying course metadata in our Online Course Organization project, which aims to build an online course portal to serve the course information obtained from the Web.

The good performances of most classical learning algorithms are generally founded on high quality training data, which are clean and unbiased. The availability of such data is however becoming much harder than ever in many real world problems due to the difficulties in collecting large scale unbiased data and precisely labeling them for training. In this paper, we propose a general Contrast Co-learning (CCL) framework to refine the biased and noisy training data when an unbiased yet unlabeled data pool is available. CCL starts with multiple sets of probably biased and noisy training data and trains a set of classifiers individually. Then under the assumption that the confidently classified data samples may have higher probabilities to be correctly classified, CCL iteratively and automatically filtering out possible data noises as well as adding those confidently classified samples from the unlabeled data pool to correct the bias. Through this process, we can generate a cleaner and unbiased training dataset with theoretical guarantees. Extensive experiments on two public text datasets clearly show that CCL consistently improves the algorithmic classification performance on biased and noisy training data compared with several state-of-the-art classical algorithms.

Frequent itemset mining (FIM) is a useful tool for discovering frequently co-occurrent items. Since its inception, a number of significant FIM algorithms have been developed to speed up mining performance. Unfortunately, when the dataset size is huge, both the memory use and computational cost can still be prohibitively expensive. In this work, we propose to parallelize the FP-Growth algorithm (we call our parallel algorithm PFP) on distributed machines. PFP partitions computation in such a way that each machine executes an independent group of mining tasks. Such partitioning eliminates computational dependencies between machines, and thereby communication between them. Through empirical study on a large dataset of 802,939 Web pages and 1,021,107 tags, we demonstrate that PFP can achieve virtually linear speedup. Besides scalability, the empirical study demonstrates that PFP to be promising for supporting query recommendation for search engines.