检索结果-内蒙古大学图书馆

Characterizing Smart Contract Evolution

ACM Transactions on software engineering and Methodology 1000年

作者： Xiangping Chen Ziang Qian Peiyong Liao Yuan Huang Changlin Yang Zibin Zheng Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion School of Journalism and Communication Sun Yat-sen University China School of Software Engineering Sun Yat-sen University China School of Computer Science and Engineering Sun Yat-sen University China

Smart contracts are programs that permanently store and automatically execute on the blockchain system such as Ethereum. Due to the non-tamperable nature of the underlying blockchain, smart contracts are difficult to update once deployed, which requires redeploying the contracts and migrating the data. It means that the observation of smart contract evolution in the real world makes more sense. Hence, in this paper, we conducted the first large-scale empirical study to characterize the evolution of smart contracts in Ethereum. For evolution identification, we presented a contract similarity-based search algorithm, digEvolution, and evaluated its effectiveness with five different search strategies. Then we applied this algorithm to 80,152 on-chain contracts we collected from Ethereum, to dig out the evolution among these contracts. We then explored three research questions. We first studied whether the evolution of smart contracts is common (RQ1), then we studied how do the Gas consumption (RQ2) and the vulnerability (RQ3) of smart contracts vary during the evolution. Our research results show that the evolution of smart contracts is not very common. There are some contract components that have vulnerability but still be called by users. The Gas consumption of most smart contracts doesn’t vary during the evolution, contract is Gas-efficient before and after the evolution. The vulnerability of most smart contracts doesn’t vary during the evolution, both are secure before and after the evolution.

关键词： Smart Contract software Evolution Code Clone

来源：评论

学校读者我要写书评

暂无评论

CROSS: Feedback-Oriented Multi-Modal Dynamic Alignment in Recommendation Systems

引用

ACM Transactions on Recommender Systems 1000年

作者： Yang Li Junpeng Du Chenzhan Wang Zunlong Liu Xiaomin Zhu Chen Lin Institute of Artificial Intelligence Xiamen University Xiamen China School of Informatics Xiamen University Xiamen China School of Big Data & Software Engineering Chongqing University Chongqing China School of Information Science and Engineering Shandong Normal University Jinan China Strategic Assessments and Consultation Institute Academy of Military Science Beijing China School of Informatics Xiamen University Xiamen China National Institute for Data Science in Health and Medicine Xiamen University Xiamen China

Aligning the multi-modal content and ID embeddings is crucial in multi-modal recommendation systems. Existing solutions typically adopt a bidirectional alignment paradigm. Our prior work, FETTLE, challenges this paradigm by proposing a one-way directional alignment at the item level, thus reducing the negative impact of low-quality modalities. However, FETTLE leaves two open questions: (1) when is one-way directional alignment optimal, and (2) how to incorporate collaborative signals to enhance alignment? We present CROSS (feedbaCk-oRiented multi-mOdal alignment in recommendation SyStem), a plug-and-play framework that extends FETTLE by introducing three major advancements. First, we introduce Dynamic Item-Level Alignment, which dynamically calibrates the ’strength’ of each modality via a variance-based compensation mechanism, mitigating the risk of overshadowing weaker modalities in the early stages of training. Second, we develop Multi-grained Collaborative Alignment, which introduces a medium-granularity alignment strategy based on neighboring items that share similar user feedback profiles. This neighbor-level alignment effectively balances noisy user interactions and excessive smoothing across items. Third, we conduct extensive experiments on more real-world datasets and show that CROSS significantly boosts the performance of both collaborative filtering (CF) models and multi-modal recommendation (MRS) approaches, achieving 21.52%–70.78% average improvement on CF backbones and 8.70%–20.73% on MRS backbones. Compared with FETTLE, CROSS achieves additional improvements of 3.82%–5.24%.

关键词： Recommender Systems Multi-modal Recommendation Multi-Modality Alignment

来源：评论

学校读者我要写书评

暂无评论

Multi-view Intent Learning and Alignment with Large Langue Models for Session-based Recommendation

引用

ACM Transactions on Information Systems 1000年

作者： Shutong Qiao Wei Zhou Junhao Wen Chen Gao Qun Luo Peixuan Chen Yong Li School of Big Data & Software Chongqing University China School of Big Data & Software Chongqing University China Beijing National Research Center for Information Science and Technology Tsinghua University China Tencent China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University China

Session-based recommendation (SBR) methods often rely on user behavior data, which can struggle with the sparsity of session data, limiting performance. Researchers have identified that beyond behavioral signals, rich semantic information in item descriptions is crucial for capturing hidden user intent. While large language models (LLMs) offer new ways to leverage this semantic data, the challenges of session anonymity, short-sequence nature, and high LLM training costs have hindered the development of a lightweight, efficient LLM framework for *** address the above challenges, we propose an LLM-enhanced SBR framework that integrates semantic and behavioral signals from multiple views. This two-stage framework leverages the strengths of both LLMs and traditional SBR models while minimizing training costs. In the first stage, we use multi-view prompts to infer latent user intentions at the session semantic level, supported by an intent localization module to alleviate LLM hallucinations. In the second stage, we align and unify these semantic inferences with behavioral representations, effectively merging insights from both large and small models. Extensive experiments on two real datasets demonstrate that the LLM4SBR framework can effectively improve model performance. We release our codes along with the baselines at https://***/tsinghua-fib-lab/LLM4SBR.

关键词： Recommender System Session-based Recommendation Large Language Models data Augmentation

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Early Detection and Diagnosis of Cervical Cancer 1

引用

丛书名： Signals and Communication Technology

1000年

作者： Sejal Shah Rohit M. Thanki Anjali Diwan

来源：评论

学校读者我要写书评

暂无评论

Interpreting Deep Forest through Feature Contribution and MDI Feature Importance

引用

ACM Transactions on Knowledge Discovery from data 1000年

作者： Yi-Xiao He Shen-Huan Lyu Yuan Jiang National Key Laboratory for Novel Software Technology and School of Artificial Intelligence Nanjing University China Key Laboratory of Water Big Data Technology of Ministry of Water Resources and College of Computer Science and Software Engineering Hohai University China

Deep forest is a non-differentiable deep model that has achieved impressive empirical success across a wide variety of applications, especially on categorical/symbolic or mixed modeling tasks. Many of the application fields prefer explainable models, such as random forests with feature contributions that can provide a local explanation for each prediction, and Mean Decrease Impurity (MDI) that can provide global feature importance. However, deep forest, as a cascade of random forests, possesses interpretability only at the first layer. From the second layer on, many of the tree splits occur on the new features generated by the previous layer, which makes existing explaining tools for random forests inapplicable. To disclose the impact of the original features in the deep layers, we design a calculation method with an estimation step followed by a calibration step for each layer, and propose our feature contribution and MDI feature importance calculation tools for deep forest. Experimental results on both simulated data and real-world data verify the effectiveness of our methods.

关键词： deep forest feature importance interpretability

来源：评论

学校读者我要写书评

暂无评论

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning

引用

ACM Transactions on software engineering and Methodology 1000年

作者： Boyang Yang Haoye Tian Jiadong Ren Hongyu Zhang Jacques Klein Tegawende Bissyande Claire Le Goues Shunfu Jin School of Information Science and Engineering Yanshan University China School of Computing and Information Systems University of Melbourne Australia School of Big Data and Software Engineering Chongqing University China SnT University of Luxembourg Luxembourg School of Computer Science Carnegie Mellon University USA

Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MORepair, we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective ➊), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective ➋). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality *** apply MORepair to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on function-level and repository-level repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 11.4% to 56.0%. We further show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches, including standard fine-tuning, Fine-tune-CoT, and RepairLLaMA.

关键词： Program Repair Fine-tuning Large Language Model Open Source

来源：评论

学校读者我要写书评

暂无评论

Overlapping Aware data Placement Optimizations for LSM Tree-Based Store on ZNS SSDs

引用

ACM Transactions on Architecture and Code Optimization 1000年

作者： Jingcheng Shen Lang Yang Linbo Long Zhenhua Tan Congming Gao Kan Zhong Masao Okita Fumihiko Ino School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China School of Big Data & Software Engineering Chongqing University Chongqing China Xiamen University Xiamen China Chongqing University Chongqing China School of Information Science and Technology Osaka University Suita Japan

Solid State Drives (SSDs) based on the NVMe Zoned Namespaces (ZNS) interface can notably reduce the costs of address mapping, garbage collection, and over-provisioning by dividing the storage space into multiple zones for sequential writes and random reads. The Log-Structured Merge (LSM) tree, which is extensively used in key-value storage systems, converts random writes to sequential writes, hence a suitable scenario to utilize ZNS SSDs. However, LSM tree associated data significantly varies in lifetime due to the levels and merging mechanisms of the LSM tree. Therefore, without an accurate method to estimate data lifetime, data with disparate lifetimes may be placed in the same zone, thus causing low space utilization and high write amplification within the *** address these issues, the paper proposes two data overlapping aware optimizations to realize intelligent data placement: a zone allocation scheme and a garbage collection scheme. The key technique of these optimizations is an accurate data-lifetime estimation by considering both the associated tree level of the data and the data overlapping ratio between the data and those in the neighboring level. Using the estimation technique, the zone allocation optimization can place data with similar lifetimes in the same zone. Besides, the garbage collection optimization can reclaim zones in an adaptive manner based on overlapping ratios to reduce the amount of data migration. Experimental results demonstrate that the optimization schemes effectively reduce garbage collection-incurred data copy by average factors of 2.11 × and 1.50 × in comparison to a conventional work and a state-of-the-art work, respectively. Consequently, the proposed work successfully alleviates the write amplification effect by 18% and 6%, compared to the conventional work and the state-of-the-art work, respectively.

关键词： ZNS SSDs LSM-tree data placement garbage collection

来源：评论

学校读者我要写书评

暂无评论

Model Pruning-enabled Federated Split Learning for Resource-constrained Devices in Artificial Intelligence Empowered Edge Computing Environment

引用

ACM Transactions on Sensor Networks 1000年

作者： Yongzhe Jia Bowen Liu Xuyun Zhang Fei Dai Arif Khan Lianyong Qi Wanchun Dou State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China Department of Computing Macquarie University Sydney Australia College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China M3S Empirical Software Engineering Research Unit University of Oulu Oulu Finland College of Computer Science and Technology China University of Petroleum East China - Qingdao Campus Qingdao China

Distributed Collaborative Machine Learning (DCML) has emerged in artificial intelligence-empowered edge computing environments, such as the Industrial Internet of Things (IIoT), to process tremendous data generated by smart devices. However, parallel DCML frameworks require resource-constrained devices to update the entire Deep Neural Network (DNN) models and are vulnerable to reconstruction attacks. Concurrently, the serial DCML frameworks suffer from training efficiency problems due to their serial training nature. In this paper, we propose a Model Pruning-enabled Federated Split Learning framework (MP-FSL) to reduce resource consumption with a secure and efficient training scheme. Specifically, MP-FSL compresses DNN models by adaptive channel pruning and splits each compressed model into two parts that are assigned to the client and the server. Meanwhile, MP-FSL adopts a novel aggregation algorithm to aggregate the pruned heterogeneous models. We implement MP-FSL with a real FL platform to evaluate its performance. The experimental results show that MP-FSL outperforms the state-of-the-art frameworks in model accuracy by up to 1.35%, while concurrently reducing storage and computational resource consumption by up to 32.2% and 26.73%, respectively. These results demonstrate that MP-FSL is a comprehensive solution to the challenges faced by DCML, with superior performance in both reduced resource consumption and enhanced model performance.

关键词： Federated learning split learning model pruning edge computing

来源：评论

学校读者我要写书评

暂无评论

Cheetah: Accelerating Dynamic Graph Mining with Grouping Updates

引用

ACM Transactions on Architecture and Code Optimization 1000年

作者： Yi Zhang Xiaomeng Yi Yu Huang Jingrui Yuan Chuangyi Gui Dan Chen Long Zheng Jianhui Yue Xiaofei Liao Hai Jin Jingling Xue National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Zhejiang Lab Hangzhou China National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Software Engineering Huazhong University of Science and Technology Wuhan China Eastern Institute of Technology Ningbo China National University of Singapore Singapore Singapore Michigan Technological University Houghton United States School of Computer Science and Engieering UNSW Sydney Kensington Australia

Graph pattern mining is essential for deciphering complex networks. In the real world, graphs are dynamic and evolve over time, necessitating updates in mining patterns to reflect these changes. Traditional methods use fine-grained incremental computation to avoid full re-mining after each update, which improves speed but often overlooks potential gains from examining inter-update interactions holistically, thus missing out on overall efficiency *** this paper, we introduce Cheetah, a dynamic graph mining system that processes updates in a coarse-grained manner by leveraging exploration domains. These domains exploit the community structure of real-world graphs to uncover data reuse opportunities typically missed by existing approaches. Exploration domains, which encapsulate extensive portions of the graph relevant to updates, allow multiple updates to explore the same regions efficiently. Cheetah dynamically constructs these domains using a management module that identifies and maintains areas of redundancy as the graph changes. By grouping updates within these domains and employing a neighbor-centric expansion strategy, Cheetah minimizes redundant data accesses. Our evaluation of Cheetah across five real-world datasets shows it outperforms current leading systems by an average factor of 2.63 ×.

关键词： Graph mining system dynamic graph incremental computing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：