检索结果-内蒙古大学图书馆

Cross-Modal Retrieval-Enhanced Code Summarization Based on Joint Learning for Retrieval and Generation

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Li, Lixuan Liang, Bin Chen, Lin Zhang, Xiaofang School of Computer Science and Technology Soochow University Suzhou China The Chinese University of Hong Kong China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Code summarization refers to a task that automatically generates a natural language description of a code snippet to facilitate code comprehension. Existing methods have achieved satisfactory results by incorporating information retrieval into generative deep-learning models for reusing summaries of existing code. However, most of these existing methods employed non-learnable generic retrieval methods for content-based retrieval, resulting in a lack of diversity in the retrieved results during training, thereby reducing the generative model's ability to generalize to unknown samples. To address this issue, this paper introduces CMR-Sum: a novel Cross-Modal Retrieval-enhanced code Summarization framework based on joint learning for generation and retrieval tasks, where both two tasks are allowed to be optimized simultaneously. Specifically, we use a cross-modal retrieval module to dynamically alter retrieval results during training, which enhances the diversity of the retrieved results and maintains a relative balance between the two tasks. Furthermore, in the summary generation phase, we employ a cross-attention mechanism to generate code summaries based on the alignment between retrieved and generated summaries. We conducted experiments on three real-world datasets, comparing the performance of our method with baseline models. Additionally, we performed extensive qualitative analysis. Results from qualitative and quantitative experiments indicate that our approach effectively enhances the performance of code summarization. Our method outperforms both the generation-based and the retrieval-enhanced baselines. Further ablation experiments demonstrate the effectiveness of each component of our method. Results from sensitivity analysis experiments suggest that our approach achieves good performance without requiring extensive hyper-parameter search. The direction of utilizing retrieval-enhanced generation tasks shows great potential. It is essential to increase the div

关键词： Sensitivity analysis

SABER: Model-agnostic Backdoor Attack on Chain-of-Thought in Neural Code Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jin, Naizhu Li, Zhong Guo, Yinggang Su, Chao Zhang, Tian Zeng, Qingkai State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing210023 China School of Computer Science and Engineering Changshu Institute of Technology Jiangsu Suzhou215506 China

Recent studies have proposed integrating Chain-of-Thought (CoT) reasoning to further enhance the reliability of Code Language Models (CLMs) in generating code, a step-by-step approach that breaks down complex programming tasks into manageable sub-problems. Advances in this area have introduced CoT models, specifically designed to integrate CoT reasoning effectively into language models, achieving notable improvements in code generation. Despite these advancements, the security of CoT models has not been systematically studied. In this study, we aim to fill this gap by investigating the vulnerability of CoT models to backdoor injection in code generation tasks. To address this, we propose a model-agnostic backdoor attack method SABER (Self-Attention-BasEd backdooR) based on the self-attention mechanism. SABER begins by selecting a malicious output as the backdoor using code mutation operations. It then identifies tokens most relevant to poisoned content by analyzing self-attention scores in the CodeBERT model. Finally, it applies semantic-preserving perturbations to generate adaptive and natural triggers. Our experiments on HumanEval-CoT and OpenEval-CoT test sets demonstrate that CoT models are susceptible to backdoor attacks via data poisoning. Taking the OpenEval-CoT dataset as an example, SABER achieves an ASR of 76.19%, representing an improvement of 14.29% over RIPPLe and a substantial 23.08% enhancement compared to BadPre. Further evaluations using ONION for automated detection and human studies reveal that SABER is stealthier and harder to detect, bypassing 77.27% of automated detection, with a human detection rate of just 3.17%. Our findings reveal that backdoors can be injected into CoT models to manipulate downstream code generation tasks. This highlights the urgent need for further research to understand and mitigate the security vulnerabilities in CoT models. We advocate for increased efforts to explore the security threats facing CoT models and to devel

关键词： Semantics

DOS: Diverse Outlier Sampling for Out-of-Distribution Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang, Wenyu Cheng, Hao Chen, Mingcai Wang, Chongjun Wei, Hongxin Department of Statistics and Data Science Southern University of Science and Technology China State Key Laboratory for Novel Software Technology Nanjing University China

Modern neural networks are known to give overconfident predictions for out-of-distribution inputs when deployed in the open world. It is common practice to leverage a surrogate outlier dataset to regularize the model during training, and recent studies emphasize the role of uncertainty in designing the sampling strategy for outlier datasets. However, the OOD samples selected solely based on predictive uncertainty can be biased towards certain types, which may fail to capture the full outlier distribution. In this work, we empirically show that diversity is critical in sampling outliers for OOD detection performance. Motivated by the observation, we propose a straightforward and novel sampling strategy named DOS (Diverse Outlier Sampling) to select diverse and informative outliers. Specifically, we cluster the normalized features at each iteration, and the most informative outlier from each cluster is selected for model training with absent category loss. With DOS, the sampled outliers efficiently shape a globally compact decision boundary between ID and OOD data. Extensive experiments demonstrate the superiority of DOS, reducing the average FPR95 by up to 25.79% on CIFAR-100 with TI-300K. Copyright © 2023, The Authors. All rights reserved.

关键词： Statistics

A Swin transformer encoder-based StyleGAN for unbalanced endoscopic image enhancement

学校读者我要写书评

暂无评论

computers in Biology and Medicine 2024年 175卷 108472-108472页

作者： Deng, Bo Zheng, Xiangwei Chen, Xuanchi Zhang, Mingzhe School of Information Science and Engineering Shandong Normal University Jinan250352 China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan250352 China State Key Laboratory of High–end Server & Storage Technology Jinan250101 China

With the rapid development of artificial intelligence, automated endoscopy-assisted diagnostic systems have become an effective tool for reducing the diagnostic costs and shortening the treatment cycle of patients. Typically, the performance of these systems depends on deep learning models which are pre-trained with large-scale labeled data, for example, early gastric cancer based on endoscopic images. However, the expensive annotation and the subjectivity of the annotators lead to an insufficient and class-imbalanced endoscopic image dataset, and these datasets are detrimental to the training of deep learning models. Therefore, we proposed a Swin Transformer encoder-based StyleGAN (STE-StyleGAN) for unbalanced endoscopic image enhancement, which is composed of an adversarial learning encoder and generator. Firstly, a pre-trained Swin Transformer is introduced into the encoder to extract multi-scale features layer by layer from endoscopic images. The features are subsequently fed into a mapping block for aggregation and recombination. Secondly, a self-attention mechanism is applied to the generator, which adds detailed information of the image layer by layer through recoded features, enabling the generator to autonomously learn the coupling between different image regions. Finally, we conducted extensive experiments on a private intestinal metaplasia grading dataset from a Grade-A tertiary hospital. The experimental results show that the images generated by STE-StyleGAN are closer to the initial image distribution, achieving a Fréchet Inception Distance (FID) value of 100.4. Then, these generated images are used to enhance the initial dataset to improve the robustness of the classification model, and achieved a top accuracy of 86 %. © 2024 Elsevier Ltd

关键词： Image enhancement

GRAVMAD: GROUNDED SPATIAL VALUE MAPS GUIDED ACTION DIFFUSION FOR GENERALIZED 3D MANIPULATION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Yangtao Chen, Zixuan Yin, Junhui Huo, Jing Tian, Pinzhuo Shi, Jieqi Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Suzhou China School of Computer Engineering and Science Shanghai University Shanghai China

Robots’ ability to follow language instructions and execute diverse 3D manipulation tasks is vital in robot learning. Traditional imitation learning-based methods perform well on seen tasks but struggle with novel, unseen ones due to variability. Recent approaches leverage large foundation models to assist in understanding novel tasks, thereby mitigating this issue. However, these methods lack a task-specific learning process, which is essential for an accurate understanding of 3D environments, often leading to execution failures. In this paper, we introduce GravMAD, a sub-goal-driven, language-conditioned action diffusion framework that combines the strengths of imitation learning and foundation models. Our approach breaks tasks into sub-goals based on language instructions, allowing auxiliary guidance during both training and inference. During training, we introduce Sub-goal keypose Discovery to identify key sub-goals from demonstrations. Inference differs from training, as there are no demonstrations available, so we use pre-trained foundation models to bridge the gap and identify sub-goals for the current task. In both phases, GravMaps are generated from sub-goals, providing GravMAD with more flexible 3D spatial guidance compared to fixed 3D positions. Empirical evaluations on RLBench show that GravMAD significantly outperforms state-of-the-art methods, with a 28.63% improvement on novel tasks and a 13.36% gain on tasks encountered during training. Evaluations on real-world robotic tasks further show that GravMAD can reason about real-world tasks, associate them with relevant visual information, and generalize to novel tasks. These results demonstrate GravMAD’s strong multi-task learning and generalization in 3D manipulation. Video demonstrations are available at: https://***. © 2024, CC BY.

关键词： Demonstrations

KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mai, Chengcheng Wang, Yuxiang Gong, Ziyu Wang, Hanxiang Huang, Yihua Nanjing Normal University School of Computer Science and Electronic Informatics China State Key Laboratory for Novel Software Technology Nanjing University China Nanjing University School of Computer Science China

Document-level relation extraction (Doc-RE) aims to extract relations between entities across multiple sentences. Therefore, Doc-RE requires more comprehensive reasoning abilities like humans, involving complex cross-sentence interactions between entities, contexts, and external general knowledge, compared to the sentence-level RE. However, most existing Doc-RE methods focus on optimizing single reasoning ability, but lack the ability to utilize external knowledge for comprehensive reasoning on long documents. To solve these problems, a knowledge retrieval augmented method, named KnowRA, was proposed with comprehensive reasoning to autonomously determine whether to accept external knowledge to assist DocRE. Firstly, we constructed a document graph for semantic encoding and integrated the co-reference resolution model to augment the co-reference reasoning ability. Then, we expanded the document graph into a document knowledge graph by retrieving the external knowledge base for commonsense reasoning and a novel knowledge filtration method was presented to filter out irrelevant knowledge. Finally, we proposed the axis attention mechanism to build direct and indirect associations with intermediary entities for achieving cross-sentence logical reasoning. Extensive experiments conducted on two datasets verified the effectiveness of our method compared to the state-of-the-art baselines. Our code is available at https://***/r/KnowRA. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases 23

学校读者我要写书评

暂无评论

Domain Adaptive Code Completion via Language Models and Deco...

Proceedings of the 38th IEEE/ACM International Conference on Automated software Engineering

作者： Ze Tang Jidong Ge Shangqing Liu Tingwei Zhu Tongtong Xu Liguo Huang Bin Luo National Key Laboratory for Novel Software Technology Nanjing University China Nanyang Technological University Singapore Huawei Software Engineering Application Technology China Department of Computer Science Southern Methodist University USA

ISBN: (纸本)9798350329964

Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, due to the lack of domain-specific knowledge, they may not be optimal in completing code that requires intensive domain knowledge for example completing the library names. Although there are several works that have confirmed the effectiveness of fine-tuning techniques to adapt language models for code completion in specific domains. They are limited by the need for constant fine-tuning of the model when the project is in constant *** address this limitation, in this paper, we propose kNM-LM, a retrieval-augmented language model (R-LM), that integrates domain knowledge into language models without fine-tuning. Different from previous techniques, our approach is able to automatically adapt to different language models and domains. Specifically, it utilizes the in-domain code to build the retrieval-based database decoupled from LM, and then combines it with LM through Bayesian inference to complete the code. The extensive experiments on the completion of intra-project and intra-scenario have confirmed that kNM-LM brings about appreciable enhancements when compared to CodeGPT and UnixCoder. A deep analysis of our tool including the responding speed, storage usage, specific type code completion, and API invocation completion has confirmed that kNM-LM provides satisfactory performance, which renders it highly appropriate for domain adaptive code completion. Furthermore, our approach operates without the requirement for direct access to the language model's parameters. As a result, it can seamlessly integrate with black-box code completion models, making it easy to integrate our approach as a plugin to further enhance the performance of these models.

关键词： domain adaptive code completion

CopGAT: Co-propagation Self-supervised Graph Attention Network

学校读者我要写书评

暂无评论

CopGAT: Co-propagation Self-supervised Graph Attention Netwo...

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Baoming Zhang Ming Xu Mingcai Chen Mingyuan Chen Chongjun Wang Department of Computer Science and Technology State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Graph Attention Network (GAT) is one of the state-of-the-art architectures for Graph Neural Networks (GNNs). In this paper, we first propose Label Purity to explore the relationship between the graph attention and the node labels. By tracking the label purity of graph attention, we observe that graph attention suppresses message passing between inter-class nodes in the graph with homophily. Upon such basis, we further improve graph attention's capability to capture label information by designing a self-supervised graph attention loss. We propose a novel approach based on self-supervised graph attention loss, Co-propagation Self-supervised Graph Attention Network (CopGAT), which explicitly restrains message passing between inter-class nodes. The Co-propagation means propagating node representations in Euclidean space and pseudo labels in probability simplex via the shared attention matrix, combining Message Passing Neural Networks and Label Propagation Algorithm under the graph attention framework. Constrained with the self-supervised graph attention loss generated by co-propagation, our CopGAT enhances the ability of GAT to attenuate the influence of structural noise. Furthermore, our self-supervised graph attention loss can be extended to other graph attention models in a plug-and-play manner. Experimental results demonstrate that our Cop GAT outperforms previous state-of-the-art methods on five benchmark datasets for the semi-supervised node classification task.

关键词： Message passing Benchmark testing Graph neural networks Task analysis

Cooperative Task Offloading for Internet of Vehicles in Cloud-edge Computing 23

学校读者我要写书评

暂无评论

Cooperative Task Offloading for Internet of Vehicles in Clou...

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Gu, Linjie Xu, Xiaolong Qi, Lianyong Zhang, Yiwen Zhang, Xuyun Dou, Wanchun Changwang School of Honors Nanjing University of Information Science and Technology Nanjing China School of Computer and Software Nanjing University of Information Science and Technology Nanjing China School of Information Science and Engineering Qufu Normal University China School of Computer Science and Technology Anhui University Anhui China Macquarie University The Department of Computing Sydney Australia Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

ISBN: (纸本)9781665494571

In order to support computing-intensive and service-sensitive Internet of Vehicles (IoV) applications, Digital Twin and edge computing are attractive solutions. Most of the existing IoV service offloading solutions only consider edge-cloud collaboration, but the cooperation between small cell eNodeB(SCeNB) nodes should not be ignored. Through reasonable cooperative computing between nodes, service delays far lower than offloading tasks to the cloud can be obtained. We generate and maintain the simulation of cooperation between SCeNB nodes by constructing a Digital twin to simulate SCeNB nodes in the small cell manager (SCM), thereby realizing user task offloading positions, sub-channel allocation and computing resource allocation. After that, we proposed an algorithm AUC-AC based on the dominant actor critic network and the auction-mechanism. In the DT of each SCeNB node, the global strategy is learned via deep reinforcement learning model. Numerical results show that our proposed experimental scheme is better than several baseline algorithms in terms of service delay. © 2021 IEEE.

关键词： Cloud computing Smart cities Computational modeling Reinforcement learning Digital twins Delays Numerical models