检索结果-内蒙古大学图书馆

How to Mitigate Information Loss in knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Manzong Bu, Chenyang He, Yi Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data [Hefei University of Technology Ministry of Education China School of Data Science William & Mary WilliamsburgVA United States

knowledge Graph (KG)-augmented Large Language Models (LLMs) have recently propelled significant advances in complex reasoning tasks, thanks to their broad domain knowledge and contextual awareness. Unfortunately, current methods often assume KGs to be complete, which is impractical given the inherent limitations of KG construction and the potential loss of contextual cues when converting unstructured text into entity-relation triples. In response, this paper proposes the Triple Context Restoration and Query-driven Feedback (TCR-QF) framework, which reconstructs the textual context underlying each triple to mitigate information loss, while dynamically refining the KG structure by iteratively incorporating query-relevant missing knowledge. Experiments on five benchmark question-answering datasets substantiate the effectiveness of TCR-QF in KG and LLM integration, where it achieves a 29.1% improvement in Exact Match and a 15.5% improvement in F1 over its state-of-the-art GraphRAG competitors. © 2025, CC BY.

关键词： knowledge graph

LLMIdxAdvis: Resource-Efficient Index Advisor Utilizing Large Language Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Xinxin Li, Haoyang Zhang, Jing Huang, Xinmei Zhang, Tieying Chen, Jianjun Shi, Rui Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China ByteDance China

Index recommendation is essential for improving query performance in database management systems (DBMSs) through creating an optimal set of indexes under specific constraints. Traditional methods, such as heuristic and learning-based approaches, are effective but face challenges like lengthy recommendation time, resource-intensive training, and poor generalization across different workloads and database schemas. To address these issues, we propose LLMIdxAdvis, a resource-efficient index advisor that uses large language models (LLMs) without extensive fine-tuning. LLMIdxAdvis frames index recommendation as a sequence-to-sequence task, taking target workload, storage constraint, and corresponding database environment as input, and directly outputting recommended indexes. It constructs a high-quality demonstration pool offline, using GPT-4-Turbo to synthesize diverse SQL queries and applying integrated heuristic methods to collect both default and refined labels. During recommendation, these demonstrations are ranked to inject database expertise via in-context learning. Additionally, LLMIdxAdvis extracts workload features involving specific column statistical information to strengthen LLM’s understanding, and introduces a novel inference scaling strategy combining vertical scaling (via "Index-Guided Major Voting" and Best-of-N) and horizontal scaling (through iterative "self-optimization" with database feedback) to enhance reliability. Experiments on 3 OLAP and 2 real-world benchmarks reveal that LLMIdxAdvis delivers competitive index recommendation with reduced runtime, and generalizes effectively across different workloads and database schemas. Copyright © 2025, The Authors. All rights reserved.

关键词： Query languages

Towards a Theoretical Understanding of Semi-Supervised Learning Under Class Distribution Mismatch

学校读者我要写书评

暂无评论

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第6期47卷 4853-4868页

作者： Pan Du Suyun Zhao Puhui Tan Zisen Sheng Zeyu Gan Hong Chen Cuiping Li School of Information Renmin University of China Beijing China Engineering Research Center of Database and Business Intelligence Ministry of Education (MOE) Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education (MOE) Beijing China School of Statistics Renmin University of China Beijing China

Semi-supervised learning (SSL) confronts a formidable challenge under class distribution mismatch, wherein unlabeled data contain numerous categories absent in the labeled dataset. Traditional SSL methods undergo performance deterioration in such mismatch scenarios due to the invasion of those instances from unknown categories. Despite some technical efforts to enhance SSL by mitigating the invasion, the profound theoretical analysis of SSL under class distribution mismatch is still under study. Accordingly, in this work, we propose Bi- Objective Optimization Mechanism (BOOM) to theoretically analyze the excess risk between the empirical optimal solution and the population-level optimal solution. Specifically, BOOM reveals that the SSL error is the essential contributor behind excess risk, resulting from both the pseudo-labeling error and invasion error. Meanwhile, BOOM unveils that the optimization objectives of SSL under mismatch are binary: high-quality pseudo-labels and adaptive weights on the unlabeled instances, which contribute to alleviating the pseudo-labeling error and the invasion error, respectively. Moreover, BOOM explicitly discovers the fundamental factors crucial for optimizing the bi-objectives, guided by which an approach is then proposed as a strong baseline for SSL under mismatch. Extensive experiments on benchmark and real datasets confirm the effectiveness of our proposed algorithm.

关键词： Training Labeling Semisupervised learning Predictive models Optimization Perturbation methods Entropy data models Annotations Upper bound

OmniSQL: Synthesizing High-quality Text-to-SQL data at Scale

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Haoyang Wu, Shang Zhang, Xiaokang Huang, Xinmei Zhang, Jing Jiang, Fuxin Wang, Shuai Zhang, Tieying Chen, Jianjun Shi, Rui Chen, Hong Li, Cuiping Engineering Research Center of Database and Business Intelligence MOE China School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China ByteDance Inc China

Text-to-SQL, the task of translating natural language questions into SQL queries, plays a crucial role in enabling non-experts to interact with databases. While recent advancements in large language models (LLMs) have significantly enhanced text-to-SQL performance, existing approaches face notable limitations in real-world text-to-SQL applications. Prompting-based methods often depend on closed-source LLMs, which are expensive, raise privacy concerns, and lack customization. Fine-tuning-based methods, on the other hand, suffer from poor generalizability due to the limited coverage of publicly available training data. To overcome these challenges, we propose a novel and scalable text-to-SQL data synthesis framework for automatically synthesizing large-scale, high-quality, and diverse datasets without extensive human intervention. Using this framework, we introduce SynSQL-2.5M, the first million-scale text-to-SQL dataset, containing 2.5 million samples spanning over 16,000 synthetic databases. Each sample includes a database, SQL query, natural language question, and chain-of-thought (CoT) solution. Leveraging SynSQL-2.5M, we develop OmniSQL, a powerful open-source text-to-SQL model available in three sizes: 7B, 14B, and 32B. Extensive evaluations across nine datasets demonstrate that OmniSQL achieves state-of-the-art performance, matching or surpassing leading closed-source and open-source LLMs, including GPT-4o and DeepSeek-V3, despite its smaller size. We release all code, datasets, and models to support further research. Copyright © 2025, The Authors. All rights reserved.

关键词： Structured Query Language

Disentangled Noisy Correspondence Learning

学校读者我要写书评

暂无评论

IEEE Transactions on Image Processing 2025年 34卷 2602-2615页

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong Xi’an Jiaotong University School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi’an710049 China SGIT AI Lab China State Grid Corporation of China State Grid Shaanxi Electric Power Company Limited Shaanxi China University of Science and Technology of China School of Information Science and Technology China Department of Computer Vision China Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of modality-invariant information (MII) and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal inputs for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL’s efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. © 1992-2012 IEEE.

关键词： Information theory

Joint Double Auction-Based Channel Selection in Wireless Monitoring Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Network and Service Management 2025年

作者： Xia, Na Chen, Lei Li, Meng Yin, Yutao Zhang, Ke Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data China State Grid Electric Power Research Institute Co. Ltd Hefei230088 China

In wireless networks, utilizing sniffers for fault analysis, traffic traceback, and resource optimization is a crucial task. However, existing centralized algorithms cannot be applied to high-density wireless networks. Therefore, distributed optimization of channel selection to maximize the monitoring rate of sensors in Wireless Monitoring Networks (WMNs) is a challenge. This paper proposes a joint double auction-based distributed channel selection algorithm (J2A-CS) to maximize overall quality of monitoring (QoM). First, sniffers are redundantly deployed in WMNs, and an initial channel allocation strategy is formulated. Subsequently, sniffers collectively act as buyers and sellers at different stages. Finally, buyers bid asynchronously, and sellers settle synchronously to maximize the seller's marginal revenue and update the channel selection scheme. As a distributed channel selection algorithm, J2A-CS addresses the highest overall QoM issue in WMNs, demonstrating high scalability and fault tolerance. Simulation results show that J2A-CS significantly improves QoM compared to existing distributed algorithms and outperforms centralized algorithms in high-density scenarios. © 2004-2012 IEEE.

关键词： Sales

LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hu, Yuxuan Zhang, Jing Chen, Xiaodong Zhao, Zhe Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China Engineering Research Center of Database and Business Intelligence Beijing China Tencent AI Lab Beijing China

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with additional masking mechanisms. Despite these successes, such approaches suffer from an increased memory and computation overhead, which affects efficiency of LoRA methods. In response to this limitation, we introduce LoRS, an innovative method designed to achieve both memory and computation efficiency when fine-tuning sparse LLMs. To mitigate the substantial memory and computation demands associated with preserving sparsity, our approach incorporates strategies of weight recompute and computational graph rearrangement. In addition, we also improve the effectiveness of LoRS through better adapter initialization. These innovations lead to a notable reduction in memory and computation consumption during the fine-tuning phase, all while achieving performance levels that outperform existing LoRA approaches. © 2025, CC BY.

关键词： Problem oriented languages

Predicting microRNA-Disease Associations Through Multi-View Feature Fusion and Matrix Completion on Graph Convolutional Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Computational Biology and Bioinformatic...

IEEE Transactions on Computational Biology and Bioinformatics 2025年第1期22卷 151-159页

作者： Shifei Ding Chuangui Cao Fan Sun Xuan Li Xindong Wu School of Computer Science and Technology China University of Mining and Technology Xuzhou China Mine Digitization Engineering Research Center of Ministry of Education Xuzhou China Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei China

Since the regulatory roles of microRNAs in complex human diseases have been gradually demonstrated, more and more enlightening models were developed for predicting microRNA-disease associations. These models can inform bio-logical studies on the differential expression of microRNAs. In this paper, a graph convolutional network-based model using multi-view feature fusion and matrix completion, FMCGCN for brevity, is proposed. First of all, graph autoencoders are used to learn multiple embeddings from different networks. For convenience, attention mechanisms are used to fuse them. As a result, multi-view features constructed from different perspectives are aggregated. Then, the fused embedding is fed into the graph convolutional network to aggregate local information. This fused embedding is thought to facilitate feature extraction for graph convolutional networks. Finally, feature and nuclear norm minimization, a method for matrix completion, is used to obtain the prediction matrix. Additionally, evaluation results under 5-fold cross-validation prove that FMCGCN outperforms current models in several metrics. Furthermore, case studies for esophageal neoplasms and pancreatic neoplasms also demonstrate the validity of our model.

关键词： Diseases Semantics Predictive models Kernel Topology Graph convolutional networks Feature extraction Learning systems Biological system modeling Reliability

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on Adaptive Perturbation on Federated Graph Learning 25

学校读者我要写书评

暂无评论

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on ...

Proceedings of the ACM on Web Conference 2025

作者： Ken Li Bin Shi Jiazhe Wei Bo Dong School of Computer Science and Technology Xi'an Jiaotong University Xi'an China and Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an China School of Computer Science and Technology Xi'an Jiaotong University Xi'an China and Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China School of Distance Education Xi'an Jiaotong University Xi'an China and Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China

ISBN: (纸本)9798400712746

Federated Graph Learning (FedGL) is an emerging Federated Learning (FL) framework that learns the graph data from various clients to train better Graph Neural Networks(GNNs) model. Owing to concerns regarding the security of such framework, numerous studies have attempted to execute backdoor attacks on FedGL, with a particular focus on distributed backdoor attacks. However, all existing methods posting distributed backdoor attack on FedGL only focus on injecting distributed backdoor triggers into the training data of each malicious client, which will cause model performance degradation on original task and is not always effective when confronted with robust federated learning defense algorithms, leading to low success rate of attack. What's more, the backdoor signals introduced by the malicious clients may be smoothed out by other clean signals from the honest clients, which potentially undermining the performance of the *** address the above significant shortcomings, we propose a non-intrusive graph distributed backdoor attack(NI-GDBA) that does not require backdoor triggers to be injected in the training data. Our attack trains an adaptive perturbation trigger generator model for each malicious client to learn the natural backdoor from the GNN model downloading from the server with the malicious client's local data. In contrast to traditional distributed backdoor attacks on FedGL via trigger injection in training data, our attack on different datasets such as Molecules and Bioinformatics have higher attack success rate, stronger persistence and stealth, and has no negative impact on the performance of the global GNN model. We also explore the robustness of NI-GDBA under different defense strategies, and based on our extensive experimental studies, we show that our attack method is robust to current federated learning defense methods, thus it is necessary to consider non-intrusive distributed backdoor attacks on FedGL as a novel threat that requires custom de

关键词： backdoor attacks