检索结果-内蒙古大学图书馆

Heterogeneous Graph Reinforcement Learning for Dependency-aware Multi-task Allocation in Spatial Crowdsourcing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Yong Zhu, Zhengqiu Gao, Chen Wang, En Huang, Jincai Wang, Fei-Yue College of Systems Engineering National University of Defense Technology Hunan Province Changsha410073 China BNRist Tsinghua University Beijing100084 China College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Spatial Crowdsourcing (SC) is gaining traction in both academia and industry, with tasks on SC platforms becoming increasingly complex and requiring collaboration among workers with diverse skills. Recent research works address complex tasks by dividing them into subtasks with dependencies and assigning them to suitable workers. However, the dependencies among subtasks and their heterogeneous skill requirements, as well as the need for efficient utilization of workers’ limited work time in the multi-task allocation mode, pose challenges in achieving an optimal task allocation scheme. Therefore, this paper formally investigates the problem of Dependency-aware Multi-task Allocation (DMA) and presents a well-designed framework to solve it, known as Heterogeneous Graph Reinforcement Learning-based Task Allocation (HGRL-TA). To address the challenges associated with representing and embedding diverse problem instances to ensure robust generalization, we propose a multi-relation graph model and a Compound-path-based Heterogeneous Graph Attention Network (CHANet) for effectively representing and capturing intricate relations among tasks and workers, as well as providing embedding of problem state. The task allocation decision is determined sequentially by a policy network, which undergoes simultaneous training with CHANet using the proximal policy optimization algorithm. Extensive experiment results demonstrate the effectiveness and generality of the proposed HGRL-TA in solving the DMA problem, leading to average profits that is 21.78% higher than those achieved using the metaheuristic methods. © 2024, CC BY-NC-ND.

关键词： Reinforcement learning

Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Yongguang Cao, Yueqi Li, Jindong Wang, Qi Wang, Shengsheng College of Software Jilin University Changchun130012 China College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China School of Artificial Intelligence Jilin University Changchun130012 China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence Ministry of Education Jilin University Changchun130012 China

Source-free Unsupervised Domain Adaptation (SF-UDA) aims to transfer a model’s performance from a labeled source domain to an unlabeled target domain without direct access to source samples, addressing critical data privacy concerns. However, most existing SF-UDA approaches assume the availability of abundant source domain samples, which is often impractical due to the high cost of data annotation. To address the dual challenges of limited source data and privacy concerns, we introduce a data-efficient, CLIP-powered dual-branch network (CDBN). This architecture consists of a cross-domain feature transfer branch and a target-specific feature learning branch, leveraging high-confidence target domain samples to transfer text features of source domain categories while learning target-specific soft prompts. By fusing the outputs of both branches, our approach not only effectively transfers source domain category semantic information to the target domain but also reduces the negative impacts of noise and domain gaps during target training. Furthermore, we propose an unsupervised optimization strategy driven by accurate classification and diversity, preserving the classification capability learned from the source domain while generating more confident and diverse predictions in the target domain. CDBN achieves near state-of-the-art performance with far fewer source domain samples than existing methods across 31 transfer tasks on seven datasets. © 2024, CC BY.

关键词： Adversarial machine learning

A Novel Distributed Differential Privacy Preserving Based on Random Forest in Data Centers 9th

学校读者我要写书评

暂无评论

A Novel Distributed Differential Privacy Preserving Based on...

9th International Conference on Information Technology and Quantitative Management, ITQM 2022

作者： Wang, Xi Fan, Weibei He, Jing Chi, Chi-Hung Suzhou Institute of Industrial Technology Suzhou215006 China College of Computer Nanjing University of Posts and Telecommunications Nanjing210003 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China Department of Neuroscience University of Oxford OxfordOX1 3QR United Kingdom School of Computer Nanyang Technological University Nanyang Avenue 639798 Singapore

Traditional privacy-preserving technologies have been unable to provide adequate protection and are vulnerable to background knowledge. MapReduce is parallel distributed computing model which has the advantages of good scalability and high fault tolerance. In this paper, we design a differential privacy protection based on MapReduce for the security problems faced in the distributed environment. Firstly, we propose a random forest algorithm DPMRRF that satisfies differential privacy under the MapReduce framework. Secondly, we use the MapReduce framework in the Hadoop platform to make the classification results satisfy differential privacy by adding random noise values to the leaf nodes. Finally, through the design of the feature selection scheme combined with the index mechanism, three different privacy budget allocation methods are adopted, namely, equal distribution, equal distribution and equal distribution. Experiments show that the algorithm has better classification accuracy while ensuring data availability. The proposed algorithm effectively improves the classification accuracy and operating efficiency, and greatly reduces the amount of computation. © 2022 The Authors. Published by Elsevier B.V.

关键词： MapReduce

HVIS: A Human-like Vision and Inference System for Human Motion Prediction 39

学校读者我要写书评

暂无评论

HVIS: A Human-like Vision and Inference System for Human Mot...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lyu, Kedi Chen, Haipeng Liu, Zhenguang Yin, Yifang Lin, Yukang Jiao, Yingying College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou China Institute for Infocomm Research (I2R) A*STAR Singapore Tsinghua Shenzhen International Graduate School Nanshan District Shenzhen China

ISBN: (纸本)157735897X

Grasping the intricacies of human motion, which involve perceiving spatio-temporal dependence and multi-scale effects, is essential for predicting human motion. While humans inherently possess the requisite skills to navigate this issue, it proves to be markedly more challenging for machines to emulate. To bridge the gap, we propose the Human-like Vision and Inference System (HVIS) for human motion prediction, which is designed to emulate human observation and forecast future movements. HVIS comprises two components: the human-like vision encode (HVE) module and the human-like motion inference (HMI) module. The HVE module mimics and refines the human visual process, incorporating a retina-analog component that captures spatiotemporal information separately to avoid unnecessary crosstalk. Additionally, a visual cortex-analogy component is designed to hierarchically extract and treat complex motion features, focusing on both global and local features of human poses. The HMI is employed to simulate the multi-stage learning model of the human brain. The spontaneous learning network simulates the neuronal fracture generation process for the adversarial generation of future motions. Subsequently, the deliberate learning network is optimized for hard-to-train joints to prevent misleading learning. Experimental results demonstrate that our method achieves new state-of-the-art performance, significantly outperforming existing methods by 19.8% on Human3.6M, 15.7% on CMU Mocap, and 11.1% on G3D. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Adversarial machine learning

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Yingji Du, Mengnan Wang, Xin Wang, Ying College of Computer Science and Technology Jilin University Changchun China Department of Data Science New Jersey Institute of Technology Newark United States School of Artificial Intelligence Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual Data Augmentation (CDA) to balance the training corpus. However, CDA slightly modifies the original corpus, limiting the representation distance between different demographic groups to a narrow range. As a result, the debiasing model easily fits the differences between counterfactual pairs, which affects its debiasing performance with limited text resources. In this paper, we propose an adversarial training-inspired two-stage debiasing model using Contrastive learning with Continuous Prompt Augmentation (named CCPA) to mitigate social biases in PLMs’ encoding. In the first stage, we propose a data augmentation method based on continuous prompt tuning to push farther the representation distance between sample pairs along different demographic groups. In the second stage, we utilize contrastive learning to pull closer the representation distance between the augmented sample pairs and then fine-tune PLMs’ parameters to get debiased encoding. Our approach guides the model to achieve stronger debiasing performance by adding difficulty to the training process. Extensive experiments show that CCPA outperforms baselines in terms of debiasing performance. Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs. Copyright © 2023, The Authors. All rights reserved.

关键词： Encoding (symbols)

Learning with Partial Labels from Semi-supervised Perspective

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Ximing Jiang, Yuanzhi Li, Changchun Wang, Yiyuan Ouyang, Jihong College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of MOE Jilin University China College of Information Science and Technology Northeast Normal University China Key Laboratory of Applied Statistics of MOE Northeast Normal University China

Partial Label (PL) learning refers to the task of learning from the partially labeled data, where each training instance is ambiguously equipped with a set of candidate labels but only one is valid. Advances in the recent deep PL learning literature have shown that the deep learning paradigms, e.g., self-training, contrastive learning, or class activate values, can achieve promising performance. Inspired by the impressive success of deep Semi-Supervised (SS) learning, we transform the PL learning problem into the SS learning problem, and propose a novel PL learning method, namely Partial Label learning with Semi-supervised Perspective (PLSP). Specifically, we first form the pseudo-labeled dataset by selecting a small number of reliable pseudo-labeled instances with high-confidence prediction scores and treating the remaining instances as pseudo-unlabeled ones. Then we design a SS learning objective, consisting of a supervised loss for pseudo-labeled instances and a semantic consistency regularization for pseudo-unlabeled instances. We further introduce a complementary regularization for those non-candidate labels to constrain the model predictions on them to be as small as possible. Empirical results demonstrate that PLSP significantly outperforms the existing PL baseline methods, especially on high ambiguity levels. Code available: https://***/changchunli/PLSP. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

M3oE: Multi-Domain Multi-Task Mixture-of-Experts Recommendation Framework

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Zijian Cai, Qingpeng Liu, Ziru Hu, Lantao Liu, Shuchang Zhao, Xiangyu Liu, Qidong Jiang, Peng Yu, Jiaao Zhang, Chunxu Zhao, Hongwei Gai, Kun Jilin University City University of Hong Kong Jilin China Kuaishou Technology Beijing China City University of Hong Kong Hong Kong Xi’an Jiaotong University City University of Hong Kong Xi’an China Jilin University Jilin China Beijing China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China

Multi-domain recommendation and multi-task recommendation have demonstrated their effectiveness in leveraging common information from different domains and objectives for comprehensive user modeling. Nonetheless, the practical recommendation usually faces multiple domains and tasks simultaneously, which cannot be well-addressed by current methods. To this end, we introduce M3oE, an adaptive Multi-domain Multi-task Mixture-of-Experts recommendation framework. M3oE integrates multi-domain information, maps knowledge across domains and tasks, and optimizes multiple objectives. We leverage three mixture-of-experts modules to learn common, domain-aspect, and task-aspect user preferences respectively to address the complex dependencies among multiple domains and tasks in a disentangled manner. Additionally, we design a two-level fusion mechanism for precise control over feature extraction and fusion across diverse domains and tasks. The framework’s adaptability is further enhanced by applying AutoML technique, which allows dynamic structure optimization. To the best of the authors’ knowledge, our M3oE is the first effort to solve multi-domain multi-task recommendation self-adaptively. Extensive experiments on two benchmark datasets against diverse baselines demonstrate M3oE’s superior performance. The implementation code is available to ensure reproducibility1 Copyright © 2024, The Authors. All rights reserved.

关键词： Recommender systems

Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yu, Erxin Du, Lan Jin, Yuan Wei, Zhepei Chang, Yi School of Artificial Intelligence Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University China International Center of Future Science Jilin University China Faculty of Information Technology Monash University Australia

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation learning, while being more interpretable in their predictions. In this paper, we develop a topic-informed discrete latent variable model for semantic textual similarity, which learns a shared latent space for sentence-pair representation via vector quantization. Compared with previous models limited to local semantic contexts, our model can explore richer semantic information via topic modeling. We further boost the performance of semantic similarity by injecting the quantized representation into a transformer-based language model with a well-designed semantic-driven attention mechanism. We demonstrate, through extensive experiments across various English language datasets, that our model is able to surpass several strong neural baselines in semantic textual similarity tasks. © 2022, CC0.

关键词： Semantics

Interference-Aware Opportunistic Job Placement for Shared Distributed Deep Learning Clusters

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Li, Hongliang Zhao, Hairui Sun, Ting Li, Xiang Xu, Haixiao Li, Keqin College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education Changchun China High Performance Computing Center Jilin University Changchun China Department of Computer Science State University of New York New PaltzNY12561 United States

Distributed deep learning frameworks facilitate large deep learning workloads. These frameworks support sharing one GPU device among multiple jobs to improve resource utilization. Modern deep learning training jobs consume a large amount of GPU memory. Despite that, sharing GPU memory among jobs is still possible because a training job has iterative steps that its memory usage fluctuates over time. However, resource sharing also introduces the risk of job performance degradation. Colocated jobs sharing a GPU device may suffer from different levels of interference, mainly caused by memory oversharing. How to improve resource utilization while maintaining good job performance is a novel challenge for job placement strategies. This paper studies the job placement problem. We propose an opportunistic memory sharing model to describe the time-varying job memory requirements. Based on this model, we introduce an Opportunistic Job Placement Problem (OJPP) for shared GPU clusters that seek job placement configurations using a minimum number of GPU devices and guarantee user-defined performance requirements at the same time. We propose a greedy algorithm and a heuristic algorithm with computational complexities of O(n log n) and O(n2 log n), respectively, to solve the problem. We also propose an online adjustment algorithm with the computational complexity of O(n log n) to perform updates to job placement configurations in runtime. A machine-learning-based interference prediction method is used to prepare accurate interference estimations. Extensive experiments are conducted on a GPU cluster to verify the correctness and effectiveness of our algorithms. Compared with standalone training jobs on dedicated clusters, the proposed approach reduces resource consumption by 46% in a shared cluster, while guaranteeing over 92.97% of the job performance, in terms of average job completion time. © 2023, The Authors. All rights reserved.

关键词： computational complexity