检索结果-内蒙古大学图书馆

Towards Better Dynamic Graph Learning: New Architecture and Unified Library

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Le Sun, Leilei Du, Bowen Lv, Weifeng State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University China

We propose DyGFormer, a new Transformer-based architecture for dynamic graph learning. DyGFormer is conceptually simple and only needs to learn from nodes’ historical first-hop interactions by: (i) a neighbor co-occurrence encoding scheme that explores the correlations of the source node and destination node based on their historical sequences;(ii) a patching technique that divides each sequence into multiple patches and feeds them to Transformer, allowing the model to effectively and efficiently benefit from longer histories. We also introduce DyGLib, a unified library with standard training pipelines, extensible coding interfaces, and comprehensive evaluating protocols to promote reproducible, scalable, and credible dynamic graph learning research. By performing exhaustive experiments on thirteen datasets for dynamic link prediction and dynamic node classification tasks, we find that DyGFormer achieves state-of-the-art performance on most of the datasets, demonstrating its effectiveness in capturing nodes’ correlations and long-term temporal dependencies. Moreover, some results of baselines are inconsistent with previous reports, which may be caused by their diverse but less rigorous implementations, showing the importance of DyGLib. All the used resources are publicly available at https://***/yule-BUAA/DyGLib. Copyright © 2023, The Authors. All rights reserved.

关键词： Memory architecture

Stronger Reverse Uncertainty Relation for Multiple Incompatible Observables

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Xiao Ji, Ai-Ling Zhang, Guo-Feng School of Physics State Key Laboratory of Software Development Environment Beihang University Beijing100191 China

Recently, D. Mondal *** [Phys. Rev. A. 95, 052117(2017)] creatively introduce a new interesting concept of reverse uncertainty relation which indicates that one cannot only prepare quantum states with joint small uncertainty, but also with joint great uncertainty for incompatible observables. However, the uncertainty upper bound they constructed cannot express the essence of this concept well, i.e., the upper bound will go to infinity in some cases even for incompatible observables. Here, we construct a new reverse uncertainty relation and successfully fix this "infinity" problem. Also, it is found that the reverse uncertainty relation and the normal uncertainty relation are the same in essential, and they both can be unified by the same theoretical framework. Moreover, taking advantage of this unified framework, one can construct a reverse uncertainty relation for multiple observables with any tightness required. Meanwhile, the application of the new uncertainty relation in purity detection is discussed. © 2023, CC0.

关键词：

Flow-Graph Based Optimization of Containerized Resource Scheduling: An Efficient Scheduling Algorithm for Kubernetes Clusters

学校读者我要写书评

暂无评论

Flow-Graph Based Optimization of Containerized Resource Sche...

Intelligent Computing and Robotics (ICICR), International Conference on

作者： Le Zhang Xin Ji Fang Peng Junting Li Yiting Chen Kui Zhang Big Data Center State Grid Corporation of China Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China

ISBN: (数字)9798350372274

ISBN: (纸本)9798350372281

With the widespread adoption of containerization technology and the evolution of cloud computing, efficient scheduling of containerized applications in cluster environments has become an increasingly important area of research. Kubernetes, as a mainstream container orchestration tool, faces several challenges with its default queue-based and greedy scheduling algorithm, especially in large-scale deployments, such as high latency and low scheduling robustness. This paper introduces a flow-graph-based optimization method for containerized resource scheduling, modeling the scheduling problem as a Minimum Cost Maximum Flow problem to achieve global optimization. Comparative experiments with traditional queue-based and random scheduling algorithms demonstrate the superiority of the proposed method in terms of balanced resource utilization, robustness of scheduling outcomes, and reduced algorithmic latency. This study provides a more efficient resource scheduling strategy for container orchestration tools like Kubernetes and offers a new perspective on resource management in large-scale containerized application environments.

关键词： Scheduling algorithms Optimization methods Containers Scheduling Robustness Resource management Low latency communication

SMAP: A Novel Heterogeneous Information Framework for Scenario-based Optimal Model Assignment

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qiu, Zekun Xie, Zhipu Ji, Zehua Mao, Yuhao Cheng, Ke State Key Laboratory of Software Development Environment Beihang University Haidian District Beijing100191 China

The increasing maturity of big data applications has led to a proliferation of models targeting the same objectives within the same scenarios and datasets. However, selecting the most suitable model that considers model’s features while taking specific requirements and constraints into account still poses a significant challenge. Existing methods have focused on worker-task assignments based on crowdsourcing, they neglect the scenario-dataset-model assignment problem. To address this challenge, a new problem named the Scenario-based Optimal Model Assignment (SOMA) problem is introduced and a novel framework entitled Scenario and Model Associative percepts (SMAP) is developed. SMAP is a heterogeneous information framework that can integrate various types of information to intelligently select a suitable dataset and allocate the optimal model for a specific scenario. To comprehensively evaluate models, a new score function that utilizes multi-head attention mechanisms is proposed. Moreover, a novel memory mechanism named the mnemonic center is developed to store the matched heterogeneous information and prevent duplicate matching. Six popular traffic scenarios are selected as study cases and extensive experiments are conducted on a dataset to verify the effectiveness and efficiency of SMAP and the score function. © 2023, CC BY-NC-SA.

关键词： Combinatorial optimization

software fault localization based on eigenvector centrality in complex network theory 24

学校读者我要写书评

暂无评论

Software fault localization based on eigenvector centrality ...

24th IEEE International Conference on software Quality, Reliability and Security Companion, QRS-C 2024

作者： Wu, Wentao Wang, Shihai Shao, Yuanxun Xie, Wandong School of Reliability and Systems Engineering Beihang University Beijing100191 China Science and Technology on Reliability and Environmental Engineering Laboratory China State Key Laboratory of Software Development Environment China Aerospace Science and Engineering Network Information Development CO. Ltd Beijing China Information Center of China North Industries Group Corporation Beijing China

ISBN: (纸本)9798350365658

software debugging plays a crucial role in fault localization tasks, and spectrum-based fault localization (SBFL) is a hot topic in software automation debugging research. However, existing SBFL technologies are generally limited by tie within ranks, where a large number of elements share the same suspiciousness, which in turn severely limits the performance of SBFL. To this end, we propose an SBFL model based on eigenvector centrality (FLEC). This algorithm first utilizes the statement coverage information in the program spectrum to construct a statement network, and adopts the correlation between statements as edge weights. Then, FLEC takes statement suspiciousness as node weight. On this basis, the algorithm utilizes the eigenvector centrality to calculate the weighted suspiciousness of each statement while considering both node importance and correlation between nodes. Finally, FLEC conducted experimental validation on 3 datasets of Defects4J, and the results showed an average improvement of 10.7% in ACC@N compared to the optimal baseline. © 2024 IEEE.

关键词： Program debugging

RoNID: New Intent Discovery with Generated-Reliable labels and Cluster-friendly Representations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Shun Yan, Chaoran Yang, Jian Ren, Changyu Bai, Jiaqi Li, Tongliang Li, Zhoujun State Key Lab of Software Development Environment Beihang University China School of Cyber Science and Technology Beihang University China Beijing Information Science and Technology University China

New Intent Discovery (NID) strives to identify known and reasonably deduce novel intent groups in the open-world scenario. But current methods face issues with inaccurate pseudo-labels and poor representation learning, creating a negative feedback loop that degrades overall model performance, including accuracy and the adjusted rand index. To address the aforementioned challenges, we propose a Robust New Intent Discovery (RoNID) framework optimized by an EM-style method, which focuses on constructing reliable pseudo-labels and obtaining cluster-friendly discriminative representations. RoNID comprises two main modules: reliable pseudo-label generation module and cluster-friendly representation learning module. Specifically, the pseudo-label generation module assigns reliable synthetic labels by solving an optimal transport problem in the E-step, which effectively provides high-quality supervised signals for the input of the cluster-friendly representation learning module. To learn cluster-friendly representation with strong intra-cluster compactness and large inter-cluster separation, the representation learning module combines intra-cluster and inter-cluster contrastive learning in the M-step to feed more discriminative features into the generation module. RoNID can be performed iteratively to ultimately yield a robust model with reliable pseudo-labels and cluster-friendly representations. Experimental results on multiple benchmarks demonstrate our method brings substantial improvements over previous state-of-the-art methods by a large margin of +1∼+4 points. Copyright © 2024, The Authors. All rights reserved.

关键词： Iterative methods

XCOT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chai, Linzheng Yang, Jian Sun, Tao Guo, Hongcheng Liu, Jiaheng Wang, Bing Liang, Xiannian Bai, Jiaqi Li, Tongliang Peng, Qiyao Li, Zhoujun State Key Lab of Software Development Environment Beihang University China School of New Media and Communication Tianjin University China Beijing Information Science and Technology University China

Chain-of-thought (CoT) has emerged as a powerful technique to elicit reasoning in large language models and improve a variety of downstream tasks. CoT mainly demonstrates excellent performance in English, but its usage in low-resource languages is constrained due to poor language generalization. To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (XCOT) to transfer knowledge from high-resource languages to low-resource languages. Specifically, the multilingual instruction training data (XCOT-INSTRUCT) is created to encourage the semantic alignment of multiple languages. We introduce cross-lingual in-context few-shot learning (xICL) to accelerate multilingual agreement in instruction tuning, where some fragments of source languages in examples are randomly substituted by their counterpart translations of target languages. During multilingual instruction tuning, we adopt the randomly online CoT strategy to enhance the multilingual reasoning ability of the large language model by first translating the query to another language and then answering in English. To further facilitate the language transfer, we leverage the high-resource CoT to supervise the training of low-resource languages with cross-lingual distillation. Experimental results on previous benchmarks demonstrate the superior performance of XCOT in reducing the gap among different languages, highlighting its potential to reduce the cross-lingual gap1 Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

CODESWIFT: Accelerating LLM Inference for Efficient Code Generation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Qianhui Zhang, Li Liu, Fang Lian, Xiaoli Meng, Qiaoyuanhe Jiao, Ziqian Zhou, Zetong Zhang, Borui Guo, Runlin Li, Jia School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Beihang University China Key Lab of High Confidence Software Technology Peking University China

Code generation is a latency-sensitive task that demands high timeliness, but the autoregressive decoding mechanism of Large Language Models (LLMs) leads to poor inference efficiency. Existing LLM inference acceleration methods mainly focus on standalone functions using only built-in components. Moreover, they treat code like natural language sequences, ignoring its unique syntax and semantic characteristics. As a result, the effectiveness of these approaches in code generation tasks remains limited and fails to align with real-world programming scenarios. To alleviate this issue, we propose CODESWIFT, a simple yet highly efficient inference acceleration approach specifically designed for code generation, without comprising the quality of the output. CODESWIFT constructs a multi-source datastore, providing access to both general and project-specific knowledge, facilitating the retrieval of high-quality draft sequences. Moreover, CODESWIFT reduces retrieval cost by controlling retrieval timing, and enhances efficiency through parallel retrieval and a context- and LLM preference-aware cache. Experimental results show that CODESWIFT can reach up to 2.53× and 2.54× speedup compared to autoregressive decoding in repository-level and standalone code generation tasks, respectively, outperforming state-of-the-art inference acceleration approaches by up to 88%. Our code and data are available at https://***/r/CodeSwift. Copyright © 2025, The Authors. All rights reserved.

关键词： Decoding

Permutation Invariant Training for Paraphrase Identification 48

学校读者我要写书评

暂无评论

Permutation Invariant Training for Paraphrase Identification

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Bai, Jun Yin, Chuantao Hong, Hanhua Zhang, Jianfei Li, Chen Wang, Yanmeng Rong, Wenge Beihang University State Key Laboratory of Software Development Environment Beijing China Beihang University School of Computer Science and Engineering Beijing China Beihang University Sino-French Engineer School Beijing China Ping An Technology Beijing China

ISBN: (纸本)9781728163277

Identifying sentences sharing similar meanings is crucial to speech and text understandings. Although currently popular cross-encoder solutions with pre-trained language models as backbone have achieved remarkable performance, they suffer from the lack of the permutation invariance or symmetry that is one of the most important inductive biases to such task. To alleviate this issue, in this research we propose a permutation invariant training framework, in which a symmetry regularization is introduced during training that forces the model to produce the same predictions for input sentence pairs in both forward and backward directions. Empirical studies exhibit improved performance over competitive baselines. © 2023 IEEE.

关键词： Paraphrase Identification Permutation Invariance Symmetry Regularization