Heterophily is a prevalent property of real-world graphs and is well known to impair the performance of homophilic Graph Neural Networks (GNNs). Prior work has attempted to adapt GNNs to heterophilic graphs through non-local neighbor extension or architecture refinement. However, the fundamental reasons behind misclassifications remain poorly understood. In this work, we take a novel perspective by examining recurring inductive subgraphs, empirically and theoretically showing that they act as spurious shortcuts that mislead GNNs and reinforce non-causal correlations in heterophilic graphs. To address this, we adopt a causal inference perspective to analyze and correct the biased learning behavior induced by shortcut inductive subgraphs. We propose a debiased causal graph that explicitly blocks confounding and spillover paths responsible for these shortcuts. Guided by this causal graph, we introduce Causal Disentangled GNN (CD-GNN), a principled framework that disentangles spurious inductive subgraphs from true causal subgraphs by explicitly blocking non-causal paths. By focusing on genuine causal signals, CD-GNN substantially improves the robustness and accuracy of node classification in heterophilic graphs. Extensive experiments on real-world datasets not only validate our theoretical findings but also demonstrate that our proposed CD-GNN outperforms state-of-the-art heterophily-aware baselines.

Anomaly detection is a critical task in cybersecurity, where identifying insider threats, access violations, and coordinated attacks is essential for ensuring system resilience. Graph-based approaches have become increasingly important for modeling entity interactions, yet most rely on homogeneous and static structures, which limit their ability to capture the heterogeneity and temporal evolution of real-world environments. Heterogeneous graph neural networks (HGNNs) have emerged as a promising paradigm for anomaly detection by incorporating type-aware transformations and relation-sensitive aggregation, enabling more expressive modeling of complex cyber data. However, current research on HGNN-based anomaly detection remains fragmented, with diverse modeling strategies, limited comparative evaluation, and an absence of standardized benchmarks. To address this gap, we provide a comprehensive survey of HGNN-based anomaly detection methods in cybersecurity. We introduce a taxonomy that classifies approaches by anomaly type and graph dynamics, analyze representative models, and map them to key cybersecurity applications. We also review commonly used benchmark datasets and evaluation metrics, highlighting their strengths and limitations. Finally, we identify key open challenges related to modeling, data, and deployment, and outline promising directions for future research. This survey aims to establish a structured foundation for advancing HGNN-based anomaly detection toward scalable, interpretable, and practically deployable solutions.

Sequential recommender systems (SRSs) are designed to suggest relevant items to users by analyzing their interaction sequences. However, SRSs often suffer from exposure bias in these sequences due to imbalanced item exposure and varied user activity levels, creating a self-reinforcing loop favoring popular items regardless of their true relevance. Most SRSs only focus on item dependencies to address exposure bias, while overlooking user-side exposure bias and the rich semantics behind interactions. These oversights result in a limited understanding of less active users' preferences and inaccurate preference capture for less exposed items, exacerbating exposure biases. Towards this end, we propose a novel methodLLM-enhancedDualPropensity ScoreEstimation (LDPE), which synergistically integrates Large Language Models (LLMs) and causal inference. First, LDPE leverages LLMs' superior ability in capturing rich semantics from textual data and then integrates collaborative information to generate debiased semantic-rich LLM-based user/item embeddings. With these debiased item/user embeddings, LDPE estimates time-aware debiased propensity scores from both the item and user sides. These dual propensity scores can fully mitigate exposure bias by considering item popularity, user activity levels, and temporal dynamics. Lastly, LDPE employs the transformer as the backbone of our method, incorporating estimated dual propensity scores for accurately predicting users' true preferences. Extensive experiments show that our LDPE outperforms state-of-the-art baselines in terms of recommendation performance.

Conversational recommender systems (CRSs) provide personalised recommendations by strategically querying attributes matching users’ preferences. However, this process suffers from confounding effects of time and user attributes, as users’ preferences naturally evolve over time and differ among similar users due to their unique attributes. These confounding effects distort user behaviors’ causal drivers, challenging CRSs in learning users’ true preferences and generalizable patterns. Recently, causal inference provides principled tools to clarify cause-effect relations in data, offering a promising way to address such confounding effects. In this context, we introduceCausalConversationalRecommender (CCR), which applies causal inference to model the causality between user behaviors and time/user attribute, enabling deeper understanding of user behaviors’ causal drivers. First, CCR employs stratification and matching to ensure attribute asked per round is independent from time and user attributes, mitigating their confounding effects. Following that, we apply the Average Treatment Effect (ATE) to quantify the unbiased causal impact of each unasked attribute on user preferences, identifying the attribute with the highest ATE per round as the causal-based attribute, i.e., causal driver of user behaviour. Finally, CCR iteratively refines user preferences through feedback on causal-based attributes. Extensive experiments verified CCR's robustness and personalization.

Generative adversarial network (GAN) has achieved remarkable success in generating high-quality synthetic data by learning the underlying distributions of target data. Recent efforts have been devoted to utilizing optimal transport (OT) to tackle the gradient vanishing and instability issues in GAN. They use the Wasserstein distance as a metric to measure the discrepancy between the generator distribution and the real data distribution. However, most optimal transport GANs define loss functions in Euclidean space, which limits their capability in handling high-order statistics that are of much interest in a variety of practical applications. In this article, we propose a computational framework to alleviate this issue from both theoretical and practical perspectives. Particularly, we generalize the optimal transport-based GAN from Euclidean space to the reproducing kernel Hilbert space (RKHS) and propose Hilbert Optimal Transport GAN (HOT-GAN). First, we design HOT-GAN with a Hilbert embedding that allows the discriminator to tackle more informative and high-order statistics in RKHS. Second, we prove that HOT-GAN has a closed-form kernel reformulation in RKHS that can achieve a tractable objective under the GAN framework. Third, HOT-GAN's objective enjoys the theoretical guarantee of differentiability with respect to generator parameters, which is beneficial to learn powerful generators via adversarial kernel learning. Extensive experiments are conducted, showing that our proposed HOT-GAN consistently outperforms the representative GAN works.

Predicting user satisfaction over time is crucial in news recommendations, as users’ preferences are significantly influenced by various time-variant factors. Traditional correlation-based recommenders often suffer from redundant relationships, which can undermine their effectiveness over time. This work takes a time-aware causal approach to news recommendations, treating exposed news at a predicted time as the treatment variable and the resulting user satisfaction as the outcome variable. Capturing the evolving causal effects of exposed news items on user satisfaction poses significant challenges, particularly stemming from the need to model complex dependencies among time-variant covariates, such as news popularity and recency, as well as to effectively leverage the inherent user preferences embedded in time-invariant covariates. To these ends, we propose the CA u S al T ime-aware Rec ommender, named CAST-Rec , which accounts for the causal influences of both time-variant and time-invariant covariates. Specifically, we model the intricate causal dependencies among time-variant covariates through a series of transformer-based causal blocks. For time-invariant covariates, we utilize the semantic understanding and generative capabilities of Large Language Models (LLMs) to infer inherent user preferences while mitigating potential confounding effects. Extensive experiments demonstrate the superior performance of CAST-Rec compared to various news recommendation models and across multiple LLM implementations.

Multimodal recommendation, which utilizes rich multimodal information to learn user preferences, has attracted significant attention. Most works focus on designing powerful encoders for extracting multimodal features, and simply aggregate the learned features together to make prediction. Consequently, they have a limited capacity to learn the inter-modality knowledge including the modality-shared and modality-unique knowledge. In fact, learning the modality-shared knowledge enables us to align cross-modality data for fusing heterogeneous modality features. Learning the modality-unique knowledge is equally important when recommendation tasks only involve a small amount of shared features and the necessary information is contained within specific modality. In this article, we propose Contrastive Modality-Disentangled Learning (CMDL) to overcome this critical limitation. CMDL exactly captures the inter-modality knowledge by achieving modality disentanglement. Specifically, CMDL first disentangles the initial representation into the modality-invariant and modality-specific representations. Afterwards, CMDL introduces a novel manner of contrastive learning to approximate the MI upper bounds for achieving disentanglement regularization. Building upon the proposed regularization, CMDL encourages the modality-invariant and modality-specific representations to capture the modality-shared and modality-unique knowledge respectively and to be statistically independent to each other. Empirically, extensive experiments are conducted on benchmark datasets, demonstrating the superior performance of CMDL compared with strong multimodal recommenders.

In social networks, echo chambers form when users primarily encounter information that reinforces their existing views with limited exposure to different perspectives. This self-reinforcing isolation worsens societal issues such as division and declining public discourse. Traditional approaches attempt to mitigate echo chambers by analyzing observable interaction patterns to identify their formative mechanisms. However, they overlook unobserved implicit factors, called hidden confounders in causal inference, that significantly influence content exposure and user behaviors despite not being directly captured in the data. To address this, we propose Causal Echo Diffusion Attenuator (CEDA) , a novel framework that integrates causal learning with sequential recommendations to detect and adjust for hidden confounders in social networks. Generally, CEDA comprises four key components: (1) User Dual Modelling builds comprehensive user embeddings by combining users’ attributes and structural information to fully capture behavior patterns. (2) Causal Transformer then estimates residual embeddings that account for hidden confounders, incorporating them into the Transformer as causal adjustments for unbiased user embeddings. (3) Social Diffusion Predictor uses unbiased user embeddings to jointly optimize diffusion prediction accuracy and information diversity. (4) Targeted Interventions strategically reshapes information flows to disrupt echo chambers based on the generated prediction and diversity insights. Extensive experiments demonstrate CEDA’s superior performance in both predicting information diffusion patterns and mitigating echo chambers.

Vulnerability detection is crucial for ensuring the security and reliability of software systems. Recently, Graph Neural Networks (GNNs) have emerged as a prominent code embedding approach for vulnerability detection, owing to their ability to capture the underlying semantic structure of source code. However, GNNs face significant challenges in explainability due to their inherently black-box nature. To this end, several factual reasoning-based explainers have been proposed. These explainers provide explanations for the predictions made by GNNs by analyzing the key features that contribute to the outcomes. We argue that these factual reasoning-based explanations cannot answer critical what-if questions: "What would happen to the GNN's decision if we were to alter the code graph into alternative structures?" Inspired by advancements of counterfactual reasoning in artificial intelligence, we propose CFExplainer, a novel counterfactual explainer for GNN-based vulnerability detection. Unlike factual reasoning-based explainers, CFExplainer seeks the minimal perturbation to the input code graph that leads to a change in the prediction, thereby addressing the what-if questions for vulnerability detection. We term this perturbation a counterfactual explanation, which can pinpoint the root causes of the detected vulnerability and furnish valuable insights for developers to undertake appropriate actions for fixing the vulnerability. Extensive experiments on four GNN-based vulnerability detection models demonstrate the effectiveness of CFExplainer over existing state-of-the-art factual reasoning-based explainers.

Graph collaborative filtering (GCF) has emerged as a prominent method in recommendation systems, leveraging the power of graph learning to enhance traditional collaborative filtering (CF). One common approach in GCF involves employing Graph Convolutional Networks (GCN) to learn user and item embeddings and utilize these embeddings to optimize CF models. However, existing GCN-based methods often fall short of generating satisfactory embeddings, mainly due to their limitations in capturing node dependencies and variable dependencies within the graph. Consequently, the learned embeddings are fragile in uncovering the root causes of user preferences, leading to sub-optimal performance of GCF models. In this work, we propose integrating causal modeling with the learning process of GCN-based GCF models, leveraging causality-aware graph embeddings to capture complex dependencies in recommendations. Our methodology encompasses three key designs: 1) Causal Graph conceptualization, 2) Neural Causal Model parameterization, and 3) Variational inference for the Neural Causal Model. We define a Causal Graph to model genuine dependencies in GCF models and utilize this Causal Graph to parameterize a Neural Causal Model. The proposed framework, termed Neural Causal Graph Collaborative Filtering (NCGCF), uses variational inference to approximate neural networks under the Neural Causal Model. As a result, NCGCF is able to leverage the expressive causal effects from the Causal Graph to enhance graph representation learning. Extensive experimentation on four datasets demonstrates NCGCF's ability to deliver precise recommendations consistent with user preferences.

Counterfactual explanation is one branch of interpretable machine learning that produces a perturbation sample to change the model’s original decision. The generated samples can act as a recommendation for end-users to achieve their desired outputs. Most of the current counterfactual explanation approaches are the gradient-based method, which can only optimize the differentiable loss functions with continuous variables. Accordingly, the gradient-free methods are proposed to handle the categorical variables, which however have several major limitations: (1) causal relationships among features are typically ignored when generating the counterfactuals, possibly resulting in impractical guidelines for decision-makers; (2) the counterfactual explanation algorithm requires a great deal of effort into parameter tuning for determining the optimal weight for each loss functions which must be conducted repeatedly for different datasets and settings. In this work, to address the above limitations, we propose a prototype-based counterfactual explanation framework (ProCE). ProCE is capable of preserving the causal relationship underlying the features of the counterfactual data. In addition, we design a novel gradient-free optimization based on the multi-objective genetic algorithm that generates the counterfactual explanations for the mixed-type of continuous and categorical features. Numerical experiments demonstrate that our method compares favorably with state-of-the-art methods and therefore is applicable to existing prediction models. All the source codes and data are available at https://github.com/tridungduong16/multiobj-scm-cf.

Real-world heterogeneous information networks (HINs) are modeled as heterogeneous graphs, in which features and structures are often incomplete. Existing models employ manual imputation or dynamic adjustment to populate the incomplete data. However, there are some limitations in incomplete heterogeneous graph representation learning: 1) using populated data may lose content and high-level interaction information of HINs, even lead to negative impacts on the performance of downstream tasks; and 2) existing models fail to utilize the high-order heterogeneous structures in original incomplete network data. To resolve the above issues, in this article, we proposed a lattice-based incomplete heterogeneous structural attention network (LIHAN) for learning incomplete heterogeneous node embeddings. LIHAN first constructs characteristic lattice and structure lattice by mining characteristic sets and structure sets according to the partial order relations in between. Then, an improved lattice-based heterogeneous dual-attention mechanism is used to learn the heterogeneous node representations. Extensive node classification experiments are conducted on five open datasets to verify the superior performance of the proposed LIHAN model over the state-of-the-art models. Experimental results illustrate that LIHAN outperforms other methods on the micro-F1 and macro-F1 in node classification tasks. Moreover, experiments on different levels of lattices and the parameter sensitivity analysis shows the great stability during the process of experiments.

Counterfactual explanations interpret the recommendation mechanism by exploring how minimal alterations on items or users affect recommendation decisions. Existing counterfactual explainable approaches face huge search space, and their explanations are either action-based (e.g., user click) or aspect-based (i.e., item description). We believe item attribute-based explanations are more intuitive and persuadable for users since they explain by fine-grained demographic features, e.g., brand. Moreover, counterfactual explanations could enhance recommendations by filtering out negative items. In this work, we propose a novelCounterfactual Explainable Recommendation (CERec)to generate item attribute-based counterfactual explanations meanwhile to boost recommendation performance. OurCERecoptimizes an explanation policy upon uniformly searching candidate counterfactuals within a reinforcement learning environment. We reduce the huge search space with an adaptive path sampler by using rich context information of a given knowledge graph. We also deploy the explanation policy to a recommendation model to enhance the recommendation. Extensive explainability and recommendation evaluations demonstrateCERec's ability to provide explanations consistent with user preferences and maintain improved recommendations. We release our code and processed datasets athttps://github.com/Chrystalii/CERec.

Conversational Recommender Systems (CRSs) fundamentally differ from traditional recommender systems by interacting with users in a conversational session to accurately predict their current preferences and provide personalized recommendations. Although current CRSs have achieved favorable recommendation performance, the explainability is still in its infancy stage. Most of the CRSs tend to provide coarse explanations and fail to explore the impact of minimal alterations on the recommendation decisions on items. In this paper, we are the first to incorporate the counterfactual techniques into CRS and propose a Counterfactual Explainable Conversational Recommender (CECR) to enhance the recommendation model from a counterfactual perspective. Counterfactual explanations can offer fine-grained reasons to explain users' real-time intentions, meanwhile generating counterfactual samples for augmenting the training dataset to enhance recommendation performance. Specifically, CECR adaptively learns users' preferences based on the conversation context and effectively responds to users' real-time feedback during multiple rounds of conversation. Furthermore, CECR actively generates counterfactual samples to augment the training set and thus leading to a constant improvement in recommendation performance. Empirical experiments carried out on three benchmark datasets show that our CECR outperforms state-of-the-art CRSs in terms of recommendation performance and explainability

Aesthetic attributes are crucial for aesthetics because they explicitly present some photo quality cues that a human expert might use to evaluate a photo’s aesthetic quality. However, annotating aesthetic attributes is a time-consuming, costly, and error-prone task, which leads to the issue that photos available are partially annotated with attributes. To alleviate this issue, we propose a novel semi-supervised adversarial learning method for photo aesthetic assessment from partially attribute-annotated photos, which can greatly reduce the reliance on manual attribute annotation. Specifically, the proposed method consists of a score-attributes generator$R$, a photo generator$G$, and a discriminator$D$. The score-attributes generator learns the aesthetic score and attributes simultaneously to capture their dependencies and construct better feature representations. The photo generator reconstructs the photo by feeding aesthetic attributes, score, and informative feature representation. A discriminator is used to force the convergence of the features-attributes-score tuples generated from the score-attributes generator, the photo generator, and the ground-truth distribution in labeled data for training data. The proposed method significantly outperforms the state of the art, increasing the Spearman rank-order correlation coefficient (SRCC) from the existing best reported of 0.726 to 0.761 onAesthetic and attributes databaseand 0.756 to 0.774 onAesthetic visual analysis database, respectively.

Fairness-aware recommendation alleviates discrimination issues to build trustworthy recommendation systems. Explaining the causes of unfair recommendations is critical, as it promotes fairness diagnostics, and thus secures users’ trust in recommendation models. Existing fairness explanation methods suffer high computation burdens due to the large-scale search space and the greedy nature of the explanation search process. Besides, they perform feature-level optimizations with continuous values, which are not applicable to discrete attributes such as gender and age. In this work, we adopt counterfactual explanations from causal inference and propose to generate attribute-level counterfactual explanations, adapting to discrete attributes in recommendation models. We use real-world attributes from Heterogeneous Information Networks (HINs) to empower counterfactual reasoning on discrete attributes. We propose a Counterfactual Explanation for Fairness (CFairER) that generates attribute-level counterfactual explanations from HINs for item exposure fairness. Our CFairER conducts off-policy reinforcement learning to seek high-quality counterfactual explanations, with attentive action pruning reducing the search space of candidate counterfactuals. The counterfactual explanations help to provide rational and proximate explanations for model fairness, while the attentive action pruning narrows the search space of attributes. Extensive experiments demonstrate our proposed model can generate faithful explanations while maintaining favorable recommendation performance.

Fairness-aware recommendation eliminates discrimination issues to build trustworthy recommendation systems. Existing fairness-aware approaches ignore accounting for rich user and item attributes and thus cannot capture the impact of attributes on affecting recommendation fairness. These real-world attributes severely cause unfair recommendations by favoring items with popular attributes, leading to item exposure unfairness in recommendations. Moreover, existing approaches mostly mitigate unfairness for static recommendation models, e.g., collaborative filtering. Static models can not handle dynamic user interactions with the system that reflect users’ preferences shift through time. Thus, static models are limited in their ability to adapt to user behavior shifts to gain long-run user satisfaction. As user and item attributes are largely involved in modern recommenders and user interactions are naturally dynamic, it is essential to develop a novel method that eliminates unfairness caused by attributes meanwhile embrace the dynamic modeling of user behavior shifts. In this article, we propose Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation (Fair-HINpolicy) , which uses recent advances in context-aware off-policy learning to produce fairness-aware recommendations with rich attributes from a Heterogeneous Information Network. In particular, we formulate the off-policy learning as a Constrained Markov Decision Process (CMDP) by dynamically constraining the fairness of item exposure at each iteration. We also design an attentive action sampling to reduce the search space for off-policy learning. Our solution adaptively receives HIN-augmented corrections for counterfactual risk minimization, and ultimately yields an effective policy that maximizes long-term user satisfaction. We extensively evaluate our method through simulations on large-scale real-world datasets, obtaining favorable results compared with state-of-the-art methods.

Root cause localization in microservice systems refers to finding the root cause that causes system anomalies using system information. Many methods construct a graph structure and perform random walk on it to localize the root cause. This is not suitable for larger systems due to the high computational overhead. Besides, the constructed graph is usually static which mismatches with evolving metrics. Different metrics also contribute differently to determining root cause. To address these challenges, we have developed DGERCL, a novel method that employs dynamic graph embedding to localize root causes in microservice systems. We construct a dynamic graph where nodes, edges, and features correspond to microservices, invocations, and metrics. DGERCL first gets invocation information by aggregating node embedding and features via a trainable structure. An LSTM then processes invocation information to update node embedding. We also propose a neighbor information aggregation method to enrich structure information and a self-attention-inspired mechanism to leverage the importance of metrics for better mining metrics information. Finally, a classifier maps node embedding learned by LSTM to possibilities belonging to root cause. We conduct comprehensive experiments on two microservice benchmarks. Our model achieves good results which demonstrates the effectiveness of DGERCL.

Communication networks represent communication between entities like social networks and microservice call graphs of microservice systems. Link prediction is useful in various communication network service systems such as predicting the relation between two services. Continuous-time dynamic graph (CTDG) is one form of representing temporal information in communication networks that treats them as a set of events occurring over time. Dynamic graph embedding for CTDG handles these events and disseminates event information to other nodes to get node embedding. Though dynamic graph embedding is suitable for making link prediction in communication networks, graph embedding for CTDG faces challenges such as how to model the event information dissemination process including information decaying over distance and influence of time information. To cope with this issue, we propose a CTDG-based dynamic graph embedding framework for dynamic communication networks link prediction called CTDGNN (Continuous-Time Dynamic Graph Neural Networks). In particular, we propose a self-adaptive information dissemination strategy based on node importance to update node embedding by disseminating event information. Finally, extensive numerical experiments on three real-world communication network datasets validate the effectiveness of our proposed model compared to other related methods.

Contrastive-learning-based neural networks have recently been introduced to recommender systems, due to their unique advantage of injecting collaborative signals to model deep representations, and the self-supervision nature in the learning process. Existing contrastive learning methods for recommendations are mainly proposed through introducing augmentations to the user-item (U-I) bipartite graphs. Such a contrastive learning process, however, is susceptible to bias towards popular items and users, because higher-degree users/items are subject to more augmentations and their correlations are more captured. In this paper, we advocate a Siamese Graph Contrastive Consensus Learning (SGCCL) framework, to explore intrinsic correlations and alleviate the bias effects for personalized recommendation. Instead of augmenting original U-I networks, we introduce siamese graphs, which are homogeneous relations of user-user (U-U) similarity and item-item (I-I) correlations. A contrastive consensus optimization process is also adopted to learn effective features for user-item ratings, user-user similarity, and item-item correlation. Finally, we employ the self-supervised learning coupled with the siamese item-item/user-user graph relationships, which ensures unpopular users/items are well preserved in the embedding space. Different from existing studies, SGCCL performs well on both overall and debiasing recommendation tasks resulting in a balanced recommender. Experiments on four benchmark datasets demonstrate that SGCCL outperforms state-of-the-art methods with higher accuracy and greater long-tail item/user exposure.

Graph contrastive learning has emerged as a powerful unsupervised graph representation learning tool. The key to the success of graph contrastive learning is to acquire high-quality positive and negative samples as contrasting pairs to learn the underlying structural semantics of the input graph. Recent works usually sample negative samples from the same training batch with the positive samples or from an external irrelevant graph. However, a significant limitation lies in such strategies: the unavoidable problem of sampling false negative samples. In this paper, we propose a novel method to utilize Counterfactual mechanism to generate artificial hard negative samples for Graph Contrastive learning, namely CGC. We utilize a counterfactual mechanism to produce hard negative samples, ensuring that the generated samples are similar but have labels that differ from the positive sample. The proposed method achieves satisfying results on several datasets. It outperforms some traditional unsupervised graph learning methods and some SOTA graph contrastive learning methods. We also conducted some supplementary experiments to illustrate the proposed method, including the performances of CGC with different hard negative samples and evaluations for hard negative samples generated with different similarity measurements. The implementation code is available online to ease reproducibility1.

In recommendation systems, the existence of the missing-not-at-random (MNAR) problem results in the selection bias issue, degrading the recommendation performance ultimately. A common practice to address MNAR is to treat missing entries from the so-called “exposure” perspective, i.e., modeling how an item is exposed (provided) to a user. Most of the existing approaches use heuristic models or re-weighting strategy on observed ratings to mimic the missing-at-random setting. However, little research has been done to reveal how the ratings are missing from a causal perspective. To bridge the gap, we propose an unbiased and robust method called DENC ( De-Bias Network Confounding in Recommendation ), inspired by confounder analysis in causal inference. In general, DENC provides a causal analysis on MNAR from both the inherent factors (e.g., latent user or item factors) and auxiliary network’s perspective. Particularly, the proposed exposure model in DENC can control the social network confounder meanwhile preserve the observed exposure information. We also develop a deconfounding model through the balanced representation learning to retain the primary user and item features, which enables DENC generalize well on the rating prediction. Extensive experiments on three datasets validate that our proposed model outperforms the state-of-the-art baselines.

Traditional recommendation models trained on observational interaction data have generated large impacts in a wide range of applications, it faces bias problems that cover users’ true intent and thus deteriorate the recommendation effectiveness. Existing methods track this problem as eliminating bias for the robust recommendation, e.g., by re-weighting training samples or learning disentangled representations. The disentangled representation methods as the state-of-the-art eliminate bias by revealing cause-effect of the bias generation. However, how to design the semantic-aware and unbiased representations for users’ true intents is largely unexplored. To bridge the gap, we are the first to propose an unbiased and semantic-aware disentanglement learning calledCaDSI(CausalDisentanglement forSemantics-AwareIntent Learning) from a causal perspective. Particularly, CaDSI explicitly models the causal relations underlying recommendation task, and thus produces semantic-aware representations via disentangling users’ true intents aware of specific item context. Moreover, the causal intervention mechanism is designed to eliminate confounding bias stemming from context information, which further aligns the semantic-aware representation with users’ true intent. Extensive experiments and case studies both validate the robustness and interpretability of our proposed model.

Treatment effect estimation helps answer questions, such as whether a specific treatment affects the outcome of interest. One fundamental issue in this research is to alleviate the treatment assignment bias among those treated units and controlled units. Classical causal inference methods resort to the propensity score estimation, which unfortunately tends to be misspecified when only limited overlapping exists between the treated and the controlled units. Moreover, existing supervised methods mainly consider the treatment assignment information underlying the factual space, and thus, their performance of counterfactual inference may be degraded due to overfitting of the factual results. To alleviate those issues, we build on the optimal transport theory and propose a novel causal optimal transport (CausalOT) model to estimate an individual treatment effect (ITE). With the proposed propensity measure, CausalOT can infer the counterfactual outcome by solving a novel regularized optimal transport problem, which allows the utilization of global information on observational covariates to alleviate the issue of limited overlapping. In addition, a novel counterfactual loss is designed for CausalOT to align the factual outcome distribution with the counterfactual outcome distribution. Most importantly, we prove the theoretical generalization bound for the counterfactual error of CausalOT. Empirical studies on benchmark datasets confirm that the proposed CausalOT outperforms state-of-the-art causal inference methods.

Recommender systems which captures dynamic user interest based on time-ordered user-item interactions plays a critical role in the real-world. Although existing deep learning-based recommendation systems show good performances, these methods have two main drawbacks. Firstly, user interest is the consequence of the coaction of many factors. However, existing methods do not fully explore potential influence factors and ignore the user-item interaction formation process. The coarse-grained modeling patterns cannot accurately reflect complex user interest and leads to suboptimal recommendation results. Furthermore, these methods are implicit and largely operate in a black-box fashion. It is difficult to interpret their modeling processes and recommendation results. Secondly, recommendation datasets usually exhibit scale-free distributions and some existing recommender systems take advantage of hyperbolic space to match the data distribution. But they ignore that the operations in hyperbolic space are more complex than that in Euclidean space which further increases the difficulty of model interpretation. To tackle the above shortcomings, we propose an E xplainable H yperbolic T emporal P oint P rocess for User-Item Interaction Sequence Generation (EHTPP) . Specifically, EHTPP regards each user-item interaction as an event in hyperbolic space and employs a temporal point process framework to model the probability of event occurrence. Considering that the complexity of user interest and the interpretability of the model,EHTPP explores four potential influence factors related to user interest and uses them to explicitly guide the probability calculation in the temporal point process. In order to validate the effectiveness of EHTPP, we carry out a comprehensive evaluation of EHTPP on three datasets compared with a few competitive baselines. Experimental results demonstrate the state-of-the-art performances of EHTPP.

Knowledge Graph Embedding (KGE) aims to learn representations for entities and relations. Most KGE models have gained great success, especially on extrapolation scenarios. Specifically, given an unseen triple (h, r, t), a trained model can still correctly predict t from (h, r, ?), or h from (?, r, t), such extrapolation ability is impressive. However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate. Therefore in this work, we attempt to study the KGE extrapolation of two problems: 1. How does KGE extrapolate to unseen data? 2. How to design the KGE model with better extrapolation ability? For the problem 1, we first discuss the impact factors for extrapolation and from relation, entity and triple level respectively, propose three Semantic Evidences (SEs), which can be observed from train set and provide important semantic information for extrapolation. Then we verify the effectiveness of SEs through extensive experiments on several typical KGE methods. For the problem 2, to make better use of the three levels of SE, we propose a novel GNN-based KGE model, called Semantic Evidence aware Graph Neural Network (SE-GNN). In SE-GNN, each level of SE is modeled explicitly by the corresponding neighbor pattern, and merged sufficiently by the multi-layer aggregation, which contributes to obtaining more extrapolative knowledge representation. Finally, through extensive experiments on FB15k-237 and WN18RR datasets, we show that SE-GNN achieves state-of-the-art performance on Knowledge Graph Completion task and performs a better extrapolation ability. Our code is available at https://github.com/renli1024/SE-GNN.

Graph meta-learning which is used to deal with graph few-shot learning attracts more and more research interests. Existing graph meta-learning methods mainly focus on capturing node-level relations, but they ignore task-level relations which are beneficial for improving the performance of few-shot node classification. Furthermore, contrastive learning which can learn knowledge without labeled data is suitable for few-shot scenario, but existing graph few-shot learning methods have never exploited it. To tackle above problems, in this paper, we combine conventional graph meta-learning framework with graph contrastive learning and propose a novel joint model named -${\underline T}$asklevel -${\underline R}$elations Modelling for -${\underline G}$raph ${\underline M}$eta-learning (TRGM). By constructing auxiliary contrastive pretext tasks, TRGM can fully capture the inter-task relations (task correlation and task discrepancy) and promote the primary few-shot learning. Finally, we conduct extensive experiments on six benchmark datasets to validate the effectiveness and efficiency of TRGM. Experimental results show that our model outperforms several strong baselines and achieves the new state-of-the-art.

Off-policy learning has drawn huge attention in recommender systems (RS), which provides an opportunity for reinforcement learning to abandon the expensive online training. However, off-policy learning from logged data suffers biases caused by the policy shift between the target policy and the logging policy. Consequently, most off-policy learning resorts to inverse propensity scoring (IPS) which however tends to be over-fitted over exposed (or recommended) items and thus fails to explore unexposed items.

Reinforcement learning has recently become an active topic in recommender system research, where the logged data that records interactions between items and users feedback is used to discover the policy. Much off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has been a popular research topic in reinforcement learning. However, the log entries are biased in that the logs over-represent actions favored by the recommender system, as the user feedback contains only partial information limited to the particular items exposed to the user. As a result, the policy learned from such off-line logged data tends to be biased from the true behaviour policy.

Many regression tasks encounter an asymmetric distribution of information between training and testing phases where the additional information available in training, the so-called privileged information (PI), is often inaccessible in testing. In practice, the privileged information in training data might be expressed in different formats, such as continuous, ordinal, or binary values. However, most the existing learning using privileged information (LUPI) paradigms primarily deal with the continuous form of PI, preventing them from managing variational PI, which motivates this research. Therefore, in this paper, we propose a unified framework to systematically address the aforementioned three forms of privileged information. The proposed V-SVR+ method integrates continuous, ordinal, and binary PI into the learning process of support vector regression (SVR) via three losses. For continuous privileged information, we define a linear correcting (slack) function in the privileged information space to estimate slack variables in the standard SVR method using privileged information. For the ordinal relations of privileged information, we first rank the privileged information and then, regard this ordinal privileged information as auxiliary information used in the learning process of the SVR model. For the binary or Boolean privileged information, we infer a probabilistic dependency between the privileged information and labels from the summarized privileged information knowledge. Then, we transfer the privileged information knowledge to constraints and form a constrained optimization problem. We evaluate the proposed method in three applications: music emotion recognition from songs with the help of implicit information about music elements judged by composers; multiple object recognition from images with the help of implicit information about the object’s importance conveyed by the list of manually annotated image tags; and photo aesthetic assessment enhanced by high-level aesthetic attributes hidden in photos. Experiment results demonstrate that the proposed methods are superior to the classic learning paradigm when solving practical problems.

Abstract Causal inference is capable of estimating the treatment effect (i.e., the causal effect oftreatmenton theoutcome) to benefit the decision making in various domains. One fundamental challenge in this research is that the treatment assignment bias in observational data. To increase the validity of observational studies on causal inference, representation-based methods as the state-of-the-art have demonstrated the superior performance of treatment effect estimation. Most representation-based methods assume all observed covariates are pre-treatment (i.e., not affected by the treatment) and learn a balanced representation from these observed covariates for estimating treatment effect. Unfortunately, this assumption is often too strict a requirement in practice, as some covariates are changed by doing an intervention on treatment (i.e., post-treatment). By contrast, the balanced representation learned from unchanged covariates thus biases the treatment effect estimation. In light of this, we propose a deep treatment-adaptive architecture (DTANet) that can address the post-treatment covariates and provide a unbiased treatment effect estimation. Generally speaking, the contributions of this work are threefold. First, our theoretical results guarantee DTANet can identify treatment effect from observations. Second, we introduce a novel regularization of orthogonality projection to ensure that the learned confounding representation is invariant and not being contaminated by the treatment, meanwhile mediate variable representation is informative and discriminative for predicting the outcome. Finally, we build on the optimal transport and learn a treatment-invariant representation for the unobserved confounders to alleviate the confounding bias.

Abstract Attributed graph embedding aims to learn node representation based on the graph topology and node attributes. The current mainstream GNN-based methods learn the representation of the target node by aggregating the attributes of its neighbor nodes. These methods still face two challenges: (1) In the neighborhood aggregation procedure, the attributes of each node would be propagated to its neighborhoods which may cause disturbance to the original attributes of the target node and cause over-smoothing in GNN iteration. (2) Because the representation of the target node is derived from the attributes and topology of its neighbors, the attributes and topological information of each neighbor have different effects on the representation of the target node. However, this different contribution has not been considered by the existing GNN-based methods. In this paper, we propose a novel GNN model named API-GNN (Attribute Preserving Oriented Interactive Graph Neural Network). API-GNN can not only reduce the disturbance of neighborhood aggregation to the original attribute of target node, but also explicitly model the different impacts of attribute and topology on node representation. We conduct experiments on six public real-world datasets to validate API-GNN on node classification and link prediction. Experimental results show that our model outperforms several strong baselines over various graph datasets on multiple graph analysis tasks.

Underwriting is an important process in insurance and is concerned with accepting individuals into insurance policy with tolerable claim risk. Underwriting is a tedious and labor intensive process relying on underwriters' domain knowledge and experience, thus is labor intensive and prone to error. Machine learning models are recently applied to automate the underwriting process and thus to ease the burden on the underwriters as well as improve underwriting accuracy. However, observational data used for underwriting modelling is high dimensional, sparse and incomplete, due to the dynamic evolving nature (e.g., upgrade) of business information systems. Simply applying traditional supervised learning methods e.g., logistic regression or Gradient boosting on such highly incomplete data usually leads to the unsatisfactory underwriting result, thus requiring practical data imputation for training quality improvement. In this paper, rather than choosing off-the-shelf solutions tackling the complex data missing problem, we propose an innovative Generative Adversarial Nets (GAN) framework that can capture the missing pattern from a causal perspective. Specifically, we design a structural causal model to learn the causal relations underlying the missing pattern of data. Then, we devise a Causality-aware Generative network (CaGen) using the learned causal relationship prior to generating missing values, and correct the imputed values via the adversarial learning. We also show that CaGen significantly improves the underwriting prediction in real-world insurance applications.

The Sinkhorn divergence has become a very popular metric to compare probability distributions in optimal transport. However, most works resort to the Sinkhorn divergence in Euclidean space, which greatly blocks their applications in complex data with nonlinear structure. It is therefore of theoretical demand to empower the Sinkhorn divergence with the capability of capturing nonlinear structures. We propose a theoretical and computational framework to bridge this gap. In this paper, we extend the Sinkhorn divergence in Euclidean space to the reproducing kernel Hilbert space, which we term "Hilbert Sinkhorn divergence" (HSD). In particular, we can use kernel matrices to derive a closed form expression of the HSD that is proved to be a tractable convex optimization problem. We also prove several attractive statistical properties of the proposed HSD, i.e., strong consistency, asymptotic behavior and sample complexity. Empirically, our method yields state-of-the-art performances on image classification and topological data analysis.

Causal inference methods are widely applied in various decision-making domains such as precision medicine, optimal policy and economics. Central to these applications is the treatment effect estimation of intervention strategies. Current estimation methods are mostly restricted to the deterministic treatment, which however, is unable to address the stochastic space treatment policies. Moreover, previous methods can only make binary yes-or-no decisions based on the treatment effect, lacking the capability of providing fine-grained effect estimation degree to explain the process of decision making. In our study, we therefore advance the causal inference research to estimate stochastic intervention effect by devising a new stochastic propensity score and stochastic intervention effect estimator (SIE). Meanwhile, we design a customized genetic algorithm specific to stochastic intervention effect (Ge-SIO) with the aim of providing causal evidence for decision making. We provide the theoretical analysis and conduct an empirical study to justify that our proposed measures and algorithms can achieve a significant performance lift in comparison with state-of-the-art baselines.

A fundamental challenge for reinforcement learning (RL) is how to achieve efficient exploration in initially unknown environments. Most state-of-the-art RL algorithms leverage action space noise to drive exploration. The classical strategies are computationally efficient and straightforward to implement. However, these methods may fail to perform effectively in complex environments. To address this issue, we propose a novel strategy named reward space noise (RSN) for farsighted and consistent exploration in RL. By introducing the stochasticity from reward space, we are able to change agent’s understanding about environment and perturb its behaviors. We find that the simple RSN can achieve consistent exploration and scale to complex domains without intensive computational cost. To demonstrate the effectiveness and scalability of the proposed method, we implement a deep Q-learning agent with reward noise and evaluate its exploratory performance on a set of Atari games which are challenging for the naive [Formula: see text]-greedy strategy. The results show that reward noise outperforms action noise in most games and performs comparably in others. Concretely, we found that in the early training, the best exploratory performance of reward noise is obviously better than action noise, which demonstrates that the reward noise can quickly explore the valuable states and aid in finding the optimal policy. Moreover, the average scores and learning efficiency of reward noise are also higher than action noise through the whole training, which indicates that the reward noise can generate more stable and consistent performance.

Abstract User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predicting the label of identity pairs or selecting the most relevant identity pair based on the similarity scores. However, most of these methods fail to utilize the results of previously matched identities, which could contribute to the subsequent linkages in following matching steps. To address this problem, we transform user identity linkage into a sequence decision problem and propose a reinforcement learning model to optimize the linkage strategy from the global perspective. Our method makes full use of both the social network structure and the history matched identities, meanwhile explores the long-term influence of processing matching on subsequent decisions. We conduct extensive experiments on real-world datasets, the results show that our method outperforms the state-of-the-art methods.

Persistence diagram (PD) has been considered as a compact descriptor for topological data analysis (TDA). Unfortunately, PD cannot be directly used in machine learning methods since it is a multiset of points. Recent efforts have been devoted to transforming PDs into vectors to accommodate machine learning methods. However, they share one common shortcoming: the mapping of PDs to a feature representation depends on a pre-defined polynomial. To address this limitation, this paper proposes an algebraic representation for PDs, i.e., polynomial representation. In this work, we discover a set of general polynomials that vanish on vectorized PDs and extract the task-adapted feature representation from these polynomials. We also prove two attractive properties of the proposed polynomial representation, i.e., stability and linear separability. Experiments also show that our method compares favorably with state-of-the-art TDA methods.

Entity linking is the task of aligning mentions to corresponding entities in a given knowledge base. Previous studies have highlighted the necessity for entity linking systems to capture the global coherence. However, there are two common weaknesses in previous global models. First, most of them calculate the pairwise scores between all candidate entities and select the most relevant group of entities as the final result. In this process, the consistency among wrong entities as well as that among right ones are involved, which may introduce noise data and increase the model complexity. Second, the cues of previously disambiguated entities, which could contribute to the disambiguation of the subsequent mentions, are usually ignored by previous models. To address these problems, we convert the global linking into a sequence decision problem and propose a reinforcement learning model which makes decisions from a global perspective. Our model makes full use of the previous referred entities and explores the long-term influence of current selection on subsequent decisions. We conduct experiments on different types of datasets, the results show that our model outperforms state-of-the-art systems and has better generalization performance.

Matrix recovery aims to learn a low-rank structure from high dimensional data, which arises in numerous learning applications. As a popular heuristic to matrix recovery, convex relaxation involves iterative calling of singular value decomposition (SVD). Riemannian optimization based method can alleviate such expensive cost in SVD for improved scalability, which however is usually degraded by the unknown rank. This paper proposes a novel algorithm RIST that exploits the algebraic variety of low-rank manifold for matrix recovery. Particularly, RIST utilizes an efficient scheme that automatically estimate the potential rank on the real algebraic variety and tracks the favorable Riemannian submanifold. Moreover, RIST utilizes the second-order geometric characterization and achieves provable superlinear convergence, which is superior to the linear convergence of most existing methods. Extensive comparison experiments demonstrate the accuracy and ef- ficiency of RIST algorithm.

Low-rank matrix recovery (MR) has been widely used in data analysis and dimensionality reduction. As a direct heuristic to MR, convex relaxation is usually degraded by the repeated calling of singular value decomposition (SVD), especially in large-scale applications. In this paper, we propose a novel Riemannian optimization method (ROAM) for MR problem by exploiting the Riemannian geometry of the searching space. In particular, ROAM utilizes an efficient subspace tracking schema that automatically detects the unknown rank to identify the preferable geometry space. Moreover, a gradient-based optimization algorithm is proposed to obtain the latent low-rank component, which avoids the expensive full dimension of SVD. More significantly, ROAM algorithm is proved to converge under mild assumptions, which also verifies the effectiveness of ROAM. Extensive empirical results demonstrate the improved accuracy and efficiency of ROAM over convex-relaxation approaches.

As a popular heuristic to the matrix rank minimization problem, nuclear norm minimization attracts intensive research attentions. Matrix factorization based algorithms can reduce the expensive computation cost of SVD for nuclear norm minimization. However, most matrix factorization based algorithms fail to provide the theoretical guarantee for convergence caused by their non-unique factorizations. This paper proposes an efficient and accurate Linearized Grassmannian Optimization (Lingo) algorithm, which adopts matrix factorization and Grassmann manifold structure to alternatively minimize the subproblems. More specially, linearization strategy makes the auxiliary variables unnecessary and guarantees the close-form solution for low per-iteration complexity. Lingo then converts linearized objective function into a nuclear norm minimization over Grassmannian manifold, which could remedy the non-unique of solution for the low-rank matrix factorization. Extensive comparison experiments demonstrate the accuracy and efficiency of Lingo algorithm. The global convergence of Lingo is guaranteed with theoretical proof, which also verifies the effectiveness of Lingo.

Recently, much of the attention of SaaS has focused on the new business model that on-demand software enables. This trend requires the agile construction of applications which the long development cycle such as waterfall software-development model could not satisfy. This paper proposes a cooperative construction approach based on multi-level abstraction for SaaS applications, in which the tenant instance of a SaaS application will be abstracted into different levels according to its customization requirements, and then be constructed from different components and through different constructing routes with the collaboration of different participants in a SaaS system. We discuss the multi-level components model, the roles and the cooperative work, the multi-level construction method in details. We also introduce a case study of a SaaS application for supply business in automobile industry with the discussion of agile construction approaches.

Wireless sensor networks with hundreds of sensor nodes have emerged in recent years as important platforms for a wide spectrum of monitoring tasks ranging from environmental to military applications. In order to support scalability and increase lifetime of these networks, sensor nodes are preferably grouped into clusters. A large number of clustering protocols have been proposed in the literature with different aims, requirements and efficiency. Previous comparative studies of such protocols were usually based on simulation, which, however, only provides average case results on the limited state space explored. To mend this situation, in this paper, we evaluate and compare four state-of-the-art clustering protocols, i.e., LEACH, GENLEACH, HEED and PANEL, with full state space exploration. Within our analytical framework that consists of a network configuration and an energy consumption model, we aim at analyzing the correctness and performance of the investigated protocols. Our analysis is conducted formally through probabilistic model checking using PRISM and has its focus on the quantitative aspects of the protocols.