Anti-fraud machine learning systems are perpetually confronted with the significant challenge of concept drift, driven by the continuous and intense evolution of fraudulent techniques. That is, outdated models trained on historical fraudulent behaviors often fall short in addressing the evolving tactics of malicious users over time. The key issue lies in effectively tackling the rapid and significant evolution of fraudsters' behaviors to detect these emerging and unforeseen anomalies. In this paper, we propose a solution by directly accessing real-time data and introducing a lightweight plug-in approach named TRE (Test-time Retrieval-based Representation Enrichment). Considering the similarity among samples, TRE employs a retriever to efficiently identify the top-K most relevant recent samples and implements an aggregation strategy to provide neighboring embeddings to the predictor. It thus adjusts the trained classifiers during the test time, providing them with the information from the latest unlabeled data. Extensive experiments on three large-scale real-world datasets demonstrate the superiority of TRE. By consistently incorporating information from the nearest neighbors, TRE demonstrates high adaptability and surpasses existing methods in performance.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
Seeing Beyond Noise: Joint Graph Structure Evaluation and Denoising for Multimodal Recommendation
PDF ↗Multimodal Recommendation Systems (MRSs) boost traditional user-item interaction-based methods by incorporating multimodal information. However, existing methods ignore the inherent noise brought by (1) noisy semantic priors in multimodal content, and (2) noisy user interactions in history records, therefore diminishing model performance. To fill this gap, we propose to denoise MRSs by jointly EValuating structure Effectiveness and mitigating Noisy links (EVEN). Firstly, for semantic prior noise in multimodal content, EVEN builds item homogeneous consistency and denoises it by evaluating behavior-driven confidence. Secondly, for noise in user interactions, EVEN updates user feedback by denoising observed interactions following implicit contribution evaluation of high-order representations. Thirdly, EVEN performs cross-modal alignment through self-guided structure learning, reinforcing task-specific inter-modal dependency modeling and cross-modal fusion. Through extensive experiments on three widely-used datasets, EVEN achieves an average improvement of 8.95% and 5.90% in recommendation accuracy compared with LGMRec and FREEDOM, respectively, without extending the total training time.
An issue concerning the use of deep reinforcement learning (RL) agents is whether they can be trusted to perform reliably when deployed, as training environments may not reflect real-life environments. Anticipating instances outside their training scope, learning-enabled systems are often equipped with out-of-distribution (OOD) detectors that alert when a trained system encounters a state it does not recognize or in which it exhibits uncertainty. There exists limited work conducted on the problem of OOD detection within RL, with prior studies being unable to achieve a consensus on the definition of OOD execution within the context of RL. By framing our problem using a Markov Decision Process, we assume there is a transition distribution mapping each state-action pair to another state with some probability. Based on this, we consider the following definition of OOD execution within RL: A transition is OOD if its probability during real-life deployment differs from the transition distribution encountered during training. As such, we utilize conditional variational autoencoders (CVAE) to approximate the transition dynamics of the training environment and implement a conformity-based detector using reconstruction loss that is able to guarantee OOD detection with a pre-determined confidence level. We evaluate our detector by adapting existing benchmarks and compare it with existing OOD detection models for RL.
Graph fraud detection (GFD) has rapidly advanced in protecting online services by identifying malicious fraudsters. Recent supervised GFD research highlights that heterophilic connections between fraudster and user greatly impacts detection performance, where the fraudsters tend to camouflage themselves by building more connections to benign users. Despite their promising performance, their label reliance limits its application in unsupervised scenarios; Additionally, accurately capturing complex and diverse heterophily patterns without labels poses a further challenge. Therefore, we propose a Heterophily-guided Unsupervised Graph fraud dEtection approach (HUGE) for unsupervised GFD, which contains two essential components: a heterophily estimation module and an alignment-based fraud detection module. In the heterophily estimation module, we design a novel unsupervised heterophily metric called HALO, which captures the critical graph properties for GFD, enabling its outstanding ability to estimate heterophily with attributes. In the alignment-based fraud detection module, we develop a joint MLP-GNN architecture with ranking loss and asymmetric alignment loss. The ranking loss aligns the predicted fraud score with the relative order of HALO, providing an extra robustness guarantee by comparing heterophily between non-adjacent nodes. Moreover, the asymmetric alignment loss effectively utilizes structural information to alleviate the feature-smooth effects. Extensive experiments on six datasets demonstrate that HUGE consistently outperforms competitors, showcasing its effectiveness and robustness.
We present an unsupervised method for aggregating anomalies in tabular datasets by identifying the top-k tabular data quality insights. Each insight consists of a set of anomalous attributes and the corresponding subsets of records that serve as evidence to the user. The process of identifying these insight blocks is challenging due to (i) the absence of labeled anomalies, (ii) the exponential size of the subset search space, and (iii) the complex dependencies among attributes, which obscure the true sources of anomalies. Simple frequency-based methods fail to capture these dependencies, leading to inaccurate results. To address this, we introduce Tab-Shapley, a cooperative game theory based framework that uses Shapley values to quantify the contribution of each attribute to the data's anomalous nature. While calculating Shapley values typically requires exponential time, we show that our game admits a closed-form solution, making the computation efficient. We validate the effectiveness of our approach through empirical analysis on real-world tabular datasets with ground-truth anomaly labels.
Session-Based Recommendation (SBR) based on Graph Neural Networks (GNN) has become a new paradigm for recommender systems, and plays a fundamental role in e-commerce and other relevant domains. Existing graph aggregation methods primarily form node representations by capturing basic relationships between neighboring and central nodes. Despite their encouraging results, the global relationships of items and user intentions within sessions typically change over time, which degrades the effectiveness of existing embedding schemes. To resolve this challenge, we propose a Long and Short-Term Temporal Graph Neural Network (LS-TGNN) for SBR. LS-TGNN employs a novel temporal session graph to aggregate neighborhood information, and models user interests from both long and short-term perspectives. Specifically, we design long-term and short-term encoders to model the long and short-term interests of users, respectively. In order to better model the interests of users in different time dimensions, we introduce an item-granularity method that distinguishes between long and short-term interests. Extensive experiments on three widely used datasets demonstrate that LS-TGNN outperforms existing methods with a large margin.
Recently, Knowledge Graphs (KGs) have been successfully coupled with Large Language Models (LLMs) to mitigate their hallucinations and enhance their reasoning capability, e.g., KG-based retrieval-augmented framework. However, current KG-LLM frameworks lack rigorous uncertainty estimation, limiting their reliable deployment in applications where the cost of errors is significant. Directly incorporating uncertainty quantification into KG-LLM frameworks presents a challenge due to their more complex architectures and the intricate interactions between the knowledge graph and language model components. To address this crucial gap, we propose a new trustworthy KG-LLM framework, UAG (Uncertainty Aware Knowledge-Graph Reasoning), which incorporates uncertainty quantification into the KG-LLM framework. We design an uncertainty-aware multi-step reasoning framework that leverages conformal prediction to provide a theoretical guarantee on the prediction set. To manage the error rate of the multi-step process, we additionally introduce an error rate control module to adjust the error rate within the individual components. Extensive experiments show that UAG can achieve any pre-defined coverage rate while reducing the prediction set/interval size by 40% on average over the baselines.
Trust-GRS: A Trustworthy Training Framework for Graph Neural Network Based Recommender Systems Against Shilling Attacks
PDF ↗Graph neural network (GNN) based recommender systems have been widely used in diverse service platforms as they can more effectively capture users' interests. Nevertheless, recent investigations have revealed that the neighborhood aggregation and contrastive learning mechanisms render GNN-based recommender systems more vulnerable to fake profile injection attacks, i.e., shilling attacks. Despite numerous defenses against shilling attacks having emerged, these approaches still face certain challenges, such as the demand for prior knowledge and the difficulty in defending against multiple attacks. Therefore, this paper proposes a two-stage trustworthy GNN-based recommender systems training framework (Trust-GRS), which models the probability of data being fake in a zero-knowledge scenario and establishes a trustworthy neighborhood aggregation and contrastive learning. Through extensive experiments on multiple benchmark datasets against 12 state-of-the-art shilling attacks, we demonstrate that Trust-GRS substantially mitigates the influence of fake data in all attacks, up to 100%, while preserving the original recommendation performance. Benefiting from the absence of the requirement for prior knowledge, Trust-GRS holds significant application value for real-world recommendation platforms.
In recent years, there has been a burgeoning interest in multimodal recommender systems within the recommendation systems domain. These systems aim to understand user preferences by leveraging both user interaction data and multimodal information associated with items. This approach frequently results in superior recommendation accuracy compared to traditional models that rely solely on user-item interactions. Despite the advancements of these methods, there is a relatively low utilization of image features in propagating item-item characteristics, an overreliance on text feature similarity, and a frequent neglect of the deep relationships between items, users, and modalities. In response to these challenges, we introduce a novel model termed LLMs-Enhanced Hyper-Knowledge Graph Recommender for Multimodal Recommendation (DOGE). DOGE utilizes large language models (LLMs) to understand image information under the guidance of text information, generating cross-modal features that effectively enhance the relationship between text and image modalities. Subsequently, DOGE constructs a Hyper-Knowledge Graph (HKG) using user-item interaction information and modality features enhanced by large language models. This graph encompasses a wide range of item-item and user-user binary relations and hyper-relations, effectively expanding the feature propagation mechanisms and mitigating the overreliance on text modality. By learning on heterogeneous user-item graphs and homogeneous item-item, user-user graphs, DOGE enhances potential effective propagation between item features and user features, acquiring more effective feature representations of users and items. Comprehensive experimentation across three public real-world datasets illustrates that DOGE attains state-of-the-art (SOTA) performance, exhibiting a 7.2% improvement over the strongest baseline.
Uncertainty quantification in travel time estimation (TTE) aims to estimate the confidence interval for travel time, given the origin (O), destination (D), and departure time (T). Accurately quantifying this uncertainty requires generating the most likely path and assessing travel time uncertainty along the path. This involves two main challenges: 1) Predicting a path that aligns with the ground truth, and 2) modeling the impact of travel time in each segment on overall uncertainty under varying conditions. We propose DutyTTE to address these challenges. For the first challenge, we introduce a deep reinforcement learning method to improve alignment between the predicted path and the ground truth, providing more accurate travel time information from road segments to improve TTE. For the second challenge, we propose a mixture of experts guided uncertainty quantification mechanism to better capture travel time uncertainty for each segment under varying contexts. Extensive experiments on two real-world datasets demonstrate the superiority of our proposed method.
Anomaly detection has garnered significant attention for its extensive industrial application value. Most existing methods focus on single-view scenarios and fail to detect anomalies hidden in blind spots, leaving a gap in addressing the demands of multi-view detection in practical applications. Ensemble of multiple single-view models is a typical way to tackle the multi-view situation, but it overlooks the correlations between different views. In this paper, we propose a novel multi-view anomaly detection framework, Intra-view Decoupling and Inter-view Fusion (IDIF), to explore correlations among views. Our method contains three key components: 1) a proposed Consistency Bottleneck module extracting the common features of different views through information compression and mutual information maximization; 2) an Implicit Voxel Construction module fusing features of different views with prior knowledge represented in the form of voxels; and 3) a View-wise Dropout training strategy enabling the model to learn how to cope with missing views during test. The proposed IDIF achieves state-of-the-art performance on three datasets. Extensive ablation studies also demonstrate the superiority of our methods.
Previous ad auctions predominantly relied on rule-based mechanisms, which selected winning advertisements (ads) at the ad-level and subsequently combined them into page views (PVs), leading to suboptimal allocations in multi-round auctions. This limitation stems from the significant computational burden required to design ranking score rules and select winning ad sets, as well as the inability to fully capture contextual information within PVs during ad-level selection. In this paper, we propose a key-performance-indicator (KPI) based auction mechanism that selects winning PVs at the PV-level, modeling the ad allocation as a constrained optimization problem. This approach enables us to address both short-term and long-term KPIs while leveraging the comprehensive contextual information available within PVs. Based on this framework, we design GenAuction, a generative auction mechanism utilizing a Generator-Evaluator architecture powered by Transformer algorithms. The Generator swiftly generates multiple candidate PVs, while the Evaluator selects the optimal PVs based on contextual information, adhering to the objectives and KPIs of multi-round auctions. We conduct extensive experiments using real-world data and online A/B tests to validate that GenAuction efficiently handles multi-objective allocation tasks, demonstrating its efficacy and potential for real-world application.
Currently, e-commerce platforms integrate ads and organic content into a mixed list for users. While platforms seek to maximize profit from advertisers, organic items enhance user experience. To ensure long-term development, platforms aim to design mechanisms that optimize both revenue and user satisfaction. Current methods rank ads and organic items separately before integrating them. Even if each part is locally optimal, the combined result may not be globally optimal. In this paper, we come up with the Joint Integrated Regret Network (JINTER Net). Unlike traditional methods, which pre-order ads and organic items separately, JINTER Net directly selects from the combined set of candidate ads and organic items to generate an optimal list. This approach aims to optimally balance platform revenue and user experience while satisfying approximate dominant strategy incentive compatibility and individual rationality. We validate the effectiveness of JINTER Net using both synthetic data and real dataset, and our experimental results show that it significantly outperforms baseline models across multiple metrics.
Inductive Knowledge Graph Completion (KGC) aims to infer missing facts between newly emerged entities within knowledge graphs (KGs), posing a significant challenge. While recent studies have shown promising results in inferring such entities through knowledge subgraph reasoning, they suffer from (i) the semantic inconsistencies of similar relations, and (ii) noisy interactions inherent in KGs due to the presence of unconvincing knowledge for emerging entities. To address these challenges, we propose a Semantic Structure-aware Denoising Network (S2DN) for inductive KGC. Our goal is to learn adaptable general semantics and reliable structures to distill consistent semantic knowledge while preserving reliable interactions within KGs. Specifically, we introduce a semantic smoothing module over the enclosing subgraphs to retain the universal semantic knowledge of relations. We incorporate a structure refining module to filter out unreliable interactions and offer additional knowledge, retaining robust structure surrounding target links. Extensive experiments conducted on three benchmark KGs demonstrate that S2DN surpasses the performance of state-of-the-art models. These results demonstrate the effectiveness of S2DN in preserving semantic consistency and enhancing the robustness of filtering out unreliable interactions in contaminated KGs.
In today’s information-rich era, users rely heavily on recommender systems to identify relevant content. Graph structures, renowned for their ability to model intricate user-content relationships, have become essential to these systems. However, the accuracy of recommendations hinges critically on the quality of node representations within these graphs. Personalized recommendations strive to enhance uniqueness by maximizing the dissimilarity between representations (known as uniformity) while simultaneously ensuring that the representations align closely with the content users engage with (dubbed as alignment). Nevertheless, balancing these conflicting objectives remains a challenge for optimal recommendation performance. To tackle these challenges, we propose an innovative approach called SIURec, which differs significantly from previous studies. Rather than relying on manual weight selection between uniformity and alignment and optimizing uniformity solely on the final representation, SIURec adopts an adaptive adjustment method that learns the optimal weight between uniformity and alignment automatically. By optimizing uniformity at every convolutional layer, SIURec captures users’ sub-interests more effectively, ultimately leading to improved recommendation accuracy. Experimental results on four datasets demonstrate that SIURec achieves superior learning of uniformity (with an average improvement of 4.26% in accuracy compared to eleven SOTA methods) and exhibits robustness across different hyperparameter settings.
Cognitive diagnosis is a key task in computer-aided education, aimed at assessing a students' proficiency in specific knowledge concepts based on their responses to exercises. However, existing cognitive diagnosis models often overlook anomalies in students and exercises. For instance, some students might incorrectly response exercises despite having a strong grasp of the knowledge concept, or they might response correctly despite a lack of understanding. Such subtle anomalies can adversely affect the diagnostic results of the models. To address these anomalies, we conduct a qualitative analysis of how anomalous student states and exercise properties impact response outcomes using causal diagrams. We propose a framework named Anomaly Detection for Cognitive Diagnosis (AD4CD) to enhance the ability of Learning-to-Detect-Anomalous. AD4CD approaches the problem from a causal perspective, analyzing confounding paths that affect the true causal relationship between student ability and response outcomes, and designing an anomaly detection mechanism suitable for cognitive diagnostic models. Specifically, we first account for anomalous student behaviors and exercise properties and introduce response times from both students and exercises as modeling factors. By quantifying the response time distributions in high-dimensional features, we identify anomalies within skewed distributions, including both left-tail and right-tail anomalies. Using the detected anomaly scores, we comprehensively model the students' anomalous behaviors and exercise anomalies. Additionally, we reconstruct unbiased true abilities under natural conditions and use reconstruction loss as an anomaly score to assist in modeling guessing and slipping features. Lastly, AD4CD leverages a general cognitive diagnosis model as its backbone, optimizing the guessing and slipping features to provide unbiased and accurate feedback. Extensive experimental results demonstrate that AD4CD effectively captures anomalous data in the diagnostic process across three real-world datasets, enhancing the accuracy of the diagnostic results.
Session-based recommendation (SBR) is widely used in e-commerce and streaming services, with the task of performing real-time recommendations based on short-term anonymous user history data. Most existing SBR frameworks follow the pattern of learning a single representation for a specific session, which makes it difficult to capture potential multiple interests, thus preventing discriminative recommendations. Multi-Interest learning has emerged as an effective approach for addressing this issue on sequential data in recent years. However, the current Multi-Interest frameworks act terrible on session data because they may generate excessive interests. To address these issues, we proposed a model named Dynamic Multi-Interst Graph Neural Network (DMI-GNN) ,which introduces the Multi-Interest learning framework into SBR and refines it by proposing a multiple positional patterns (MPP) learning method and a Dynamic Multi-Interest (DMI) regularization.To be specific, the MPP learning layer ensures the model to obtain representations with different positional information for sessions.The DMI regularization, on the other hand, mitigates the influence of excessive interests. Experiments on three bench-mark datasets demonstrate that our methods achieve better performance on different metrics
Recent studies have highlighted significant fairness issues in Graph Transformer (GT) models, particularly against subgroups defined by sensitive features. Additionally, GTs are computationally intensive and memory-demanding, limiting their application to large-scale graphs. Our experiments demonstrate that graph partitioning can enhance the fairness of GT models while reducing computational complexity. To understand this improvement, we conducted a theoretical investigation into the root causes of fairness issues in GT models. We found that the sensitive features of higher-order nodes disproportionately influence lower-order nodes, resulting in sensitive feature bias. We propose Fairness-aware scalable GT based on Graph Partitioning (FairGP), which partitions the graph to minimize the negative impact of higher-order nodes. By optimizing attention mechanisms, FairGP mitigates the bias introduced by global attention, thereby enhancing fairness. Extensive empirical evaluations on six real-world datasets validate the superior performance of FairGP in achieving fairness compared to state-of-the-art methods.
Existing sequential recommendation models are mostly based on sequential models, which can be misled by inconsistent items in the local sequence. This study proposes GlobalDiff, a plug-and-play framework to enhance the performance of sequential models by utilizing a diffusion model to restore the global non-sequential data structure of the item universe and compensate for the local sequential context. Several novel techniques are proposed, including training construction, guided reverse approximator, and inference ensemble, to seamlessly integrate the diffusion model with the sequential model. Extensive experiments on various datasets demonstrate that GlobalDiff can enhance advanced sequential models by an average improvement of 9.67%.
Multi-domain recommendation (MDR) aims to enhance recommendation performance across various domains. However, real-world recommender systems in online platforms often need to handle dozens or even hundreds of domains, far exceeding the capabilities of traditional MDR algorithms, which typically focus on fewer than five domains. Key challenges include a substantial increase in parameter count, high maintenance costs, and intricate knowledge transfer patterns across domains. Furthermore, minor domains often suffer from data sparsity, leading to inadequate training in classical methods. To address these issues, we propose Adaptive REcommendation for All Domains with counterfactual augmentation (AREAD). AREAD employs a hierarchical structure with a limited number of expert networks at several layers, to effectively capture domain knowledge at different granularities. To adaptively capture the knowledge transfer pattern across domains, we generate and iteratively prune a hierarchical expert network selection mask for each domain during training. Additionally, counterfactual assumptions are used to augment data in minor domains, supporting their iterative mask pruning. Our experiments on two public datasets, each encompassing over twenty domains, demonstrate AREAD's effectiveness, especially in data-sparse domains.