Searcharxiv⌕ Search

arXiv subjects

Wensheng Gan

Publications and source records attributed to Wensheng Gan.

At least 19 recordsLinked to original sources
arXiv2026

GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning

The class imbalance problem refers to the disproportionate distribution of samples across different classes within a dataset, where the minority classes are significantly underrepresented. This issue is also prevalent in graph-structured data. Most graph neural networks (GNNs) implicitly assume a balanced class distribution and therefore often fail to account for the challenges introduced by class imbalance, which can lead to biased learning and degraded performance on minority classes. We identify a quality inconsistency problem in synthesized nodes, which leads to suboptimal performance under graph imbalance conditions. To mitigate this issue, we propose GraphIFE (Graph Invariant Feature Extraction), a novel framework designed to mitigate quality inconsistency in synthesized nodes. Our approach incorporates two key concepts from graph invariant learning and introduces strategies to strengthen the embedding space representation, thereby enhancing the model's ability to identify invariant features. Extensive experiments demonstrate the framework's efficiency and robust generalization, as GraphIFE consistently outperforms various baselines across multiple datasets. The code is publicly available at https://github.com/flzeng1/GraphIFE.

cs.LG↗
arXiv2026

Mining Negative Sequential Patterns to Improve Viral Genomic Feature Representation and Classification

Viruses represent the most abundant biological entities on Earth and play a pivotal role in microbial ecosystems, yet, as prominent human pathogens, they are closely linked to human morbidity and mortality. Accurate identification of viral sequences from viral genome sequences is therefore essential, but existing genome-based classification models that largely relying on composition- or frequency-based subsequence features often suffer from limited interpretability and reduced accuracy, particularly on complex or imbalanced datasets. To address these limitations, we propose GeneNSPCla (Genomic Negative Sequential Pattern-based Classification), a novel viral classification framework based on Negative Sequential Patterns (NSPs) that extracts discriminative absence-based features from nucleotide sequences of RNA viral genomes. By transforming these NSPs into numerical feature vectors and integrating them into multiple supervised classifiers, GeneNSPCla effectively captures both presence and absence signals in viral sequences. Furthermore, we propose a negative pattern mining algorithm adapted for processing genomic data: GONPM+, which can discover longer and more biologically meaningful negative sequential patterns. The experimental results demonstrate that the average accuracy of GONPM+ in 8 classifiers has improved by 10.03% compared to the original negative pattern mining algorithm and by 24.75% compared to the positive pattern mining algorithm. These findings highlight the effectiveness of incorporating absence-based sequential information, providing a new and complementary perspective for viral genome analysis and classification.

cs.DB↗
arXiv2026

Cross-level Privacy Preserving Utility Mining

Privacy-preserving utility mining (PPUM) aims to hide sensitive high-utility patterns while preserving the utility of the sanitized database. In practice, however, many datasets are associated with taxonomic information, which makes the identification and processing of generalized items more challenging. To address this, we investigate the cross-level privacy-preserving utility mining (CLPPUM) problem and propose a method for protecting generalized items. Based on different victim item selection strategies, we develop three CLPPUM algorithms: minimum RGISU first (Min-RF), maximum RGISU first (Max-RF), and best NSC first (Best-NSCF). Furthermore, to enable efficient victim item identification, a novel dictionary structure named GI-dic is designed to accelerate the computation of required utility metrics. Experimental results on multiple datasets demonstrate that the proposed algorithms successfully hide all sensitive cross-level high-utility itemsets without introducing artificial itemsets. The results also show that our method performs well on sparse datasets, and both Min-RF and Best-NSCF consistently outperform Max-RF. Overall, Min-RF achieves the best performance, particularly when the minimum utility threshold is low and the dataset is dense.

cs.DB↗
arXiv2026

Efficient Mining of Low-Utility Sequential Patterns

Discovering valuable insights from rich data is a crucial task for exploratory data analysis. Sequential pattern mining (SPM) has found widespread applications across various domains. In recent years, low-utility sequential pattern mining (LUSPM) has shown strong potential in applications such as intrusion detection and genomic sequence analysis. However, existing research in utility-based SPM focuses on high-utility sequential patterns, and the definitions and strategies used in high-utility SPM cannot be directly applied to LUSPM. Moreover, no algorithms have yet been developed specifically for mining low-utility sequential patterns. To address these problems, we formalize the LUSPM problem, redefine sequence utility, and introduce a compact data structure called the sequence-utility chain to efficiently record utility information. Furthermore, we propose three novel algorithm--LUSPM_b, LUSPM_s, and LUSPM_e--to discover the complete set of low-utility sequential patterns. LUSPM_b serves as an exhaustive baseline, while LUSPM_s and LUSPM_e build upon it, generating subsequences through shrinkage and extension operations, respectively. In addition, we introduce the maximal non-mutually contained sequence set and incorporate multiple pruning strategies, which significantly reduce redundant operations in both LUSPM_s and LUSPM_e. Finally, extensive experimental results demonstrate that both LUSPM_s and LUSPM_e substantially outperform LUSPM_b and exhibit excellent scalability. Notably, LUSPM_e achieves superior efficiency, requiring less runtime and memory consumption than LUSPM_s. Our code is available at https://github.com/Zhidong-Lin/LUSPM.

cs.DB↗
arXiv2026

Domain-Aware Hierarchical Contrastive Learning for Semi-Supervised Generalization Fault Diagnosis

Fault diagnosis under unseen operating conditions remains highly challenging when labeled data are scarce. Semi-supervised domain generalization fault diagnosis (SSDGFD) provides a practical solution by jointly exploiting labeled and unlabeled source domains. However, existing methods still suffer from two coupled limitations. First, pseudo-labels for unlabeled domains are typically generated primarily from knowledge learned on the labeled source domain, which neglects domain-specific geometric discrepancies and thus induces systematic cross-domain pseudo-label bias. Second, unlabeled samples are commonly handled with a hard accept-or-discard strategy, where rigid thresholding causes imbalanced sample utilization across domains, while hard-label assignment for uncertain samples can easily introduce additional noise. To address these issues, we propose a unified framework termed domain-aware hierarchical contrastive learning (DAHCL) for SSDGFD. Specifically, DAHCL introduces a domain-aware learning (DAL) module to explicitly capture source-domain geometric characteristics and calibrate pseudo-label predictions across heterogeneous source domains, thereby mitigating cross-domain bias in pseudo-label generation. In addition, DAHCL develops a hierarchical contrastive learning (HCL) module that combines dynamic confidence stratification with fuzzy contrastive supervision, enabling uncertain samples to contribute to representation learning without relying on unreliable hard labels. In this way, DAHCL jointly improves the quality of supervision and the utilization of unlabeled samples. Furthermore, to better reflect practical industrial scenarios, we incorporate engineering noise into the SSDGFD evaluation protocol. Extensive experiments on three benchmark datasets demonstrate that...

cs.LG↗
arXiv2026

Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift

Covariate distribution shift occurs when certain structural features present in the test set are absent from the training set. It is a common type of out-of-distribution (OOD) problem, frequently encountered in real-world graph data with complex structures. Existing research has revealed that most out-of-the-box graph neural networks (GNNs) fail to account for covariate shifts. Furthermore, we observe that existing methods aimed at addressing covariate shifts often fail to fully leverage the rich information contained within the latent space. Motivated by the potential of the latent space, we introduce a new method called MPAIACL for More Powerful Adversarial Invariant Augmentation using Contrastive Learning. MPAIACL leverages contrastive learning to unlock the full potential of vector representations by harnessing their intrinsic information. Through extensive experiments, MPAIACL demonstrates its robust generalization and effectiveness, as it performs well compared with other baselines across various public OOD datasets. The code is publicly available at https://github.com/flzeng1/MPAIACL.

cs.LG↗
arXiv2026

DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection

Prompt injection has emerged as a critical security threat to large language models (LLMs), yet existing studies predominantly focus on single-dimensional attack strategies, such as semantic rewriting or character-level obfuscation, which fail to capture the combined effects of multi-space perturbations in realistic scenarios. In addition, systematic black-box robustness evaluations of recent Chinese LLMs, such as DeepSeek, remain limited. To address these gaps, we propose PromptFuzz-SC, a semantic-character dual-space mutation framework for evaluating LLM robustness against prompt injection. The framework integrates semantic transformations (e.g., paraphrasing and word-order perturbation) with character-level obfuscation (e.g., zero-width insertion and encoding-based mutation), forming a unified and extensible mutation operator library. A hybrid search strategy combining epsilon-greedy exploration and hill-climbing refinement is adopted to efficiently discover high-quality adversarial prompts. We further introduce a unified evaluation protocol based on three metrics: misuse success rate (MSR), Average Queries to Success (AQS), and Stealth. Experimental results on DeepSeek demonstrate that dual-space mutation achieves the strongest overall attack performance among the evaluated strategies, attaining the highest mean MSR (0.189), peak MSR (0.375), and mean Stealth. Compared with semantic-only and character-only mutation, it improves mean MSR by 12.5% and 5.6%, respectively. While not consistently minimizing query cost, the proposed method achieves competitive best-case efficiency and maintains strong imperceptibility, indicating a more favorable balance between attack effectiveness and concealment. These findings highlight the importance of composite mutation strategies for robust red-teaming of LLMs and provide practical insights for the design of multi-layer defense mechanisms.

cs.CR↗
arXiv2026

Graph-Based Fraud Detection with Dual-Path Graph Filtering

Fraud detection on graph data can be viewed as a demanding task that requires distinguishing between different types of nodes. Because graph neural networks (GNNs) are naturally suited for processing information encoded in graph form through their message-passing operations, methods based on GNN models have increasingly attracted attention in the fraud detection domain. However, fraud graphs inherently exhibit relation camouflage, high heterophily, and class imbalance, causing most GNNs to underperform in fraud detection tasks. To address these challenges, this paper proposes a Graph-Based Fraud Detection Model with Dual-Path Graph Filtering (DPF-GFD). DPF-GFD first applies a beta wavelet-based operator to the original graph to capture key structural patterns. It then constructs a similarity graph from distance-based node representations and applies an improved low-pass filter. The embeddings from the original and similarity graphs are fused through supervised representation learning to obtain node features, which are finally used by an ensemble tree model to assess the fraud risk of unlabeled nodes. Unlike existing single-graph smoothing approaches, DPF-GFD introduces a frequency-complementary dual-path filtering paradigm tailored for fraud detection, explicitly decoupling structural anomaly modeling and feature similarity modeling. This design enables more discriminative and stable node representations in highly heterophilous and imbalanced fraud graphs. Comprehensive experiments on four real-world financial fraud detection datasets demonstrate the effectiveness of our proposed method.

cs.LG↗
arXiv2026

UPER: Efficient Utility-driven Partially-ordered Episode Rule Mining

Episode mining is a fundamental problem in analyzing a sequence of numerous events. For discovering strong relationships between events in a complex event sequence, episode rule mining is proposed. However, both the episode and episode rules have strict requirements for the order of events. Hence, partially-ordered episode rule mining (POERM) is designed to loosen the constraints on the ordering, i.e., events in the antecedents and consequents of the rule can be unordered, and POERM has been applied to real-life event prediction. In this paper, we consider the utility of POERM, intending to discover more valuable rules. We define the utility of POERs and propose an algorithm called UPER to discover high-utility partially-ordered episode rules. In addition, we adopt a data structure named NoList to store the necessary information, analyze the expansion of POERs in detail, and propose several pruning strategies (namely WEUP, REUCSP, and REEUP) to reduce the number of candidate rules. Finally, we conduct experiments on several datasets to demonstrate the effectivene

cs.DB↗
arXiv2026

Guided Exploration of Sequential Rules

In pattern mining, sequential rules provide a formal framework to capture the temporal relationships and inferential dependencies between items. However, the discovery process is computationally intensive. To obtain mining results efficiently and flexibly, many methods have been proposed that rely on specific evaluation metrics (i.e., ensuring results meet minimum threshold requirements). A key issue with these methods, however, is that they generate many sequential rules that are irrelevant to users. Such rules not only incur additional computational overhead but also complicate downstream analysis. In this paper, we investigate how to efficiently discover user-centric sequential rules. The original database is first processed to determine whether a target query rule is present. To prune unpromising items and avoid unnecessary expansions, we design tight and generalizable upper bounds. We introduce a novel method for efficiently generating target sequential rules using the proposed techniques and pruning strategies. In addition, we propose the corresponding mining algorithms for two common evaluation metrics: frequency and utility. We also design two rule similarity metrics to help discover the most relevant sequential rules. Extensive experiments demonstrate that our algorithms outperform state-of-the-art approaches in terms of runtime and memory usage, while discovering a concise set of sequential rules under flexible similarity settings. Targeted sequential rule search can handle sequence data with personalized features and achieve pattern discovery. The proposed solution addresses several challenges and can be applied to two common mining tasks.

cs.DB↗
arXiv2026

Discovering High-utility Sequential Rules with Increasing Utility Ratio

Utility-driven mining is an essential task in data science, as it can provide deeper insight into the real world. High-utility sequential rule mining (HUSRM) aims at discovering sequential rules with high utility and high confidence. It can certainly provide reliable information for decision-making because it uses confidence as an evaluation metric, as well as some algorithms like HUSRM and US-Rule. However, in current rule-growth mining methods, the linkage between HUSRs and their generation remains ambiguous. Specifically, it is unclear whether the addition of new items affects the utility or confidence of the former rule, leading to an increase or decrease in their values. Therefore, in this paper, we formulate the problem of mining HUSRs with an increasing utility ratio. To address this, we introduce a novel algorithm called SRIU for discovering all HUSRs with an increasing utility ratio using two distinct expansion methods, including left-right expansion and right-left expansion. SRIU also utilizes the item pair estimated utility pruning strategy (IPEUP) to reduce the search space. Moreover, for the two expansion methods, two sets of upper bounds and corresponding pruning strategies are introduced. To enhance the efficiency of SRIU, several optimizations are incorporated. These include utilizing the Bitmap to reduce memory consumption and designing a compact utility table for the mining procedure. Finally, extensive experimental results from both real-world and synthetic datasets demonstrate the effectiveness of the proposed method. Moreover, to better assess the quality of the generated sequential rules, metrics such as confidence and conviction are employed, which further demonstrate that SRIU can improve the relevance of mining results.

cs.DB↗
arXiv2026

High-utility Sequential Rule Mining Utilizing Segmentation Guided by Confidence

Within the domain of data mining, one critical objective is the discovery of sequential rules with high utility. The goal is to discover sequential rules that exhibit both high utility and strong confidence, which are valuable in real-world applications. However, existing high-utility sequential rule mining algorithms suffer from redundant utility computations, as different rules may consist of the same sequence of items. When these items can form multiple distinct rules, additional utility calculations are required. To address this issue, this study proposes a sequential rule mining algorithm that utilizes segmentation guided by confidence (RSC), which employs confidence-guided segmentation to reduce redundant utility computation. It adopts a method that precomputes the confidence of segmented rules by leveraging the support of candidate subsequences in advance. Once the segmentation point is determined, all rules with different antecedents and consequents are generated simultaneously. RSC uses a utility-linked table to accelerate candidate sequence generation and introduces a stricter utility upper bound, called the reduced remaining utility of a sequence, to address sequences with duplicate items. Finally, the proposed RSC method was evaluated on multiple datasets, and the results demonstrate improvements over state-of-the-art approaches.

cs.DB↗
arXiv2025

Enhancing Temporal Awareness in LLMs for Temporal Point Processes

Temporal point processes (TPPs) are crucial for analyzing events over time and are widely used in fields such as finance, healthcare, and social systems. These processes are particularly valuable for understanding how events unfold over time, accounting for their irregularity and dependencies. Despite the success of large language models (LLMs) in sequence modeling, applying them to temporal point processes remains challenging. A key issue is that current methods struggle to effectively capture the complex interaction between temporal information and semantic context, which is vital for accurate event modeling. In this context, we introduce TPP-TAL (Temporal Point Processes with Enhanced Temporal Awareness in LLMs), a novel plug-and-play framework designed to enhance temporal reasoning within LLMs. Rather than using the conventional method of simply concatenating event time and type embeddings, TPP-TAL explicitly aligns temporal dynamics with contextual semantics before feeding this information into the LLM. This alignment allows the model to better perceive temporal dependencies and long-range interactions between events and their surrounding contexts. Through comprehensive experiments on several benchmark datasets, it is shown that TPP-TAL delivers substantial improvements in temporal likelihood estimation and event prediction accuracy, highlighting the importance of enhancing temporal awareness in LLMs for continuous-time event modeling. The code is made available at https://github.com/chenlilil/TPP-TAL

cs.AI↗
arXiv2025

Graph Attention-based Adaptive Transfer Learning for Link Prediction

Graph neural networks (GNNs) have brought revolutionary advancements to the field of link prediction (LP), providing powerful tools for mining potential relationships in graphs. However, existing methods face challenges when dealing with large-scale sparse graphs and the need for a high degree of alignment between different datasets in transfer learning. Besides, although self-supervised methods have achieved remarkable success in many graph tasks, prior research has overlooked the potential of transfer learning to generalize across different graph datasets. To address these limitations, we propose a novel Graph Attention Adaptive Transfer Network (GAATNet). It combines the advantages of pre-training and fine-tuning to capture global node embedding information across datasets of different scales, ensuring efficient knowledge transfer and improved LP performance. To enhance the model's generalization ability and accelerate training, we design two key strategies: 1) Incorporate distant neighbor embeddings as biases in the self-attention module to capture global features. 2) Introduce a lightweight self-adapter module during fine-tuning to improve training efficiency. Comprehensive experiments on seven public datasets demonstrate that GAATNet achieves state-of-the-art performance in LP tasks. This study provides a general and scalable solution for LP tasks to effectively integrate GNNs with transfer learning. The source code and datasets are publicly available at https://github.com/DSI-Lab1/GAATNet

cs.LG↗
arXiv2025

Dual Pruning and Sorting-Free Overestimation for Average-Utility Sequential Pattern Mining

In a quantitative sequential database, numerous efficient algorithms have been developed for high-utility sequential pattern mining (HUSPM). HUSPM establishes a relationship between frequency and significance in the real world and reflects more crucial information than frequent pattern mining. However, high average-utility sequential pattern mining (HAUSPM) is deemed fairer and more valuable than HUSPM. It provides a reasonable measure for longer patterns by considering their length. In contrast to scenarios in retail business analysis, some pattern mining applications, such as cybersecurity or artificial intelligence (AI), often involve much longer sequences. Consequently, pruning strategies can exert a more pronounced impact on efficiency. This paper proposes a novel algorithm named HAUSP-PG, which adopts two complementary strategies to independently process pattern prefixes and remaining sequences, thereby achieving a dual pruning effect. Additionally, the proposed method calculates average utility upper bounds without requiring item sorting, significantly reducing computational time and memory consumption compared to alternative approaches. Through experiments conducted on both real-life and synthetic datasets, we demonstrate that the proposed algorithm could achieve satisfactory performance.

cs.DB↗
arXiv2025

Targeted Sequential Pattern Mining with High Average Utility

Incorporating utility into targeted pattern mining can address the practical limitations of traditional frequency-based approaches. However, utility-based methods often suffer from generating a large number of long and complicated sequences. To improve pattern relevance and interpretability, average utility provides a more balanced metric by considering both utility and sequence length. Moreover, incorporating user-defined query targets into the mining process enhances usability and interactivity by retaining only patterns containing user-specified goals. To address challenges related to mining efficiency in large-scale, long-sequence datasets, this study introduces average utility into targeted sequential pattern mining. A novel algorithm, TAUSQ-PG, is designed to find targeted high average utility sequential patterns. It incorporates efficient filtering and pruning strategies, tighter upper bound models, as well as novel specialized evaluation metrics and query flags tailored to this task. Extensive comparative experiments on different datasets demonstrate that TAUSQ-PG effectively controls the candidate set size, thereby reducing redundant sequence generation and significantly improving runtime and memory efficiency.

cs.DB↗
arXiv2025

Large Language Models for Robotics: A Survey

The human ability to learn, generalize, and control complex manipulation tasks through multi-modality feedback suggests a unique capability, which we refer to as dexterity intelligence. Understanding and assessing this intelligence is a complex task. Amidst the swift progress and extensive proliferation of large language models (LLMs), their applications in the field of robotics have garnered increasing attention. LLMs possess the ability to process and generate natural language, facilitating efficient interaction and collaboration with robots. Researchers and engineers in the field of robotics have recognized the immense potential of LLMs in enhancing robot intelligence, human-robot interaction, and autonomy. Therefore, this comprehensive review aims to summarize the applications of LLMs in robotics, delving into their impact and contributions to key areas such as robot control, perception, decision-making, and planning. This survey first provides an overview of the background and development of LLMs for robotics, followed by a discussion of their benefits and recent advancements in LLM-based robotic models. It then explores various techniques, employed in perception, decision-making, control, and interaction, as well as cross-module coordination in practical tasks. Finally, we review current applications of LLMs in robotics and outline potential challenges they may face in the near future. Embodied intelligence represents the future of intelligent systems, and LLM-based robotics is one of the most promising yet challenging paths toward achieving it.

cs.RO↗
arXiv2025

Global-focal Adaptation with Information Separation for Noise-robust Transfer Fault Diagnosis

Existing transfer fault diagnosis methods typically assume either clean data or sufficient domain similarity, which limits their effectiveness in industrial environments where severe noise interference and domain shifts coexist. To address this challenge, we propose an information separation global-focal adversarial network (ISGFAN), a robust framework for cross-domain fault diagnosis under noise conditions. ISGFAN is built on an information separation architecture that integrates adversarial learning with an improved orthogonal loss to decouple domain-invariant fault representation, thereby isolating noise interference and domain-specific characteristics. To further strengthen transfer robustness, ISGFAN employs a global-focal domain-adversarial scheme that constrains both the conditional and marginal distributions of the model. Specifically, the focal domain-adversarial component mitigates category-specific transfer obstacles caused by noise in unsupervised scenarios, while the global domain classifier ensures alignment of the overall distribution. Experiments conducted on three public benchmark datasets demonstrate that the proposed method outperforms other prominent existing approaches, confirming the superiority of the ISGFAN framework. Data and code are available at https://github.com/JYREN-Source/ISGFAN

cs.AI↗