检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yuan, Xiaosong Shen, Chen Yan, Shaotian Zhang, Xiaofeng Xie, Liang Wang, Wenxiao Guan, Renchu Wang, Ying Ye, Jieping College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering MoE Jilin University China Alibaba Cloud Computing China Shanghai Jiao Tong University China College of Computer Science and Technology Zhejiang University of Technology China College of Software Zhejiang University China

Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in real-world reasoning tasks. Nonetheless, the efficacy of a singular, task-level prompt uniformly applied across the whole of instances is inherently limited since one prompt cannot be a good partner for all, a more appropriate approach should consider the interaction between the prompt and each instance meticulously. This work introduces an instance-adaptive prompting algorithm as an alternative zero-shot CoT reasoning scheme by adaptively differentiating good and bad prompts. Concretely, we first employ analysis on LLMs through the lens of information flow to detect the mechanism under zero-shot CoT reasoning, in which we discover that information flows from question to prompt and question to rationale jointly influence the reasoning results most. We notice that a better zero-shot CoT reasoning needs the prompt to obtain semantic information from the question, and then the rationale aggregates sufficient information from the question directly and via the prompt indirectly. On the contrary, lacking any of those would probably lead to a bad one. Stem from that, we further propose an instance-adaptive prompting strategy (IAP) for zero-shot CoT reasoning. Experiments conducted with LLaMA-2, LLaMA-3, and Qwen on math, logic, and commonsense reasoning tasks (e.g., GSM8k, MMLU, Causal Judgement) obtain consistent improvement, demonstrating that the instance-adaptive zero-shot CoT prompting performs better than other task-level methods with some curated prompts or sophisticated procedures, showing the significance of our findings in the zero-shot CoT reasoning mechanism. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel graph oversampling framework for node classification in class-imbalanced graphs

引用

Science China(Information Sciences) 2024年第6期67卷 214-229页

作者： Riting XIA Chunxu ZHANG Yan ZHANG Xueyan LIU Bo YANG Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University College of Artificial Intelligence Jilin University College of Computer Science and Technology Jilin University College of Communication Engineering Jilin University

Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling. In this paper, we propose a novel graph oversampling framework, termed distribution alignment-based oversampling for node classification in classimbalanced graphs(named Graph-DAO). Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs. Additionally, we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes. To our best knowledge, it is the first to use the sum-product network to solve the class-imbalanced problem in node classification. A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.

关键词： graph neural network class-imbalanced graphs sum-product network oversampling node classification

来源：评论

学校读者我要写书评

暂无评论

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling 38

Decision Mamba: Reinforcement Learning via Hybrid Selective ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Huang, Sili Hu, Jifeng Yang, Zhejian Yang, Liwei Luo, Tao Chen, Hechang Sun, Lichao Yang, Bo Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education China School of Artificial Intelligence Jilin University China Institute of High Performance Computing Agency for Science Technology and Research Singapore Lehigh University BethlehemPA United States

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement in online environments by providing task contexts, such as multiple trajectories, called in-context RL. However, due to the quadratic computation complexity of attention in transformers, current in-context RL methods suffer from huge computational costs as the task horizon increases. In contrast, the Mamba model is renowned for its efficient ability to process long-term dependencies, which provides an opportunity for in-context RL to solve tasks that require long-term memory. To this end, we first implement Decision Mamba (DM) by replacing the backbone of Decision Transformer (DT). Then, we propose a Decision Mamba-Hybrid (DM-H) with the merits of transformers and Mamba in high-quality prediction and long-term memory. Specifically, DM-H first generates high-value sub-goals from long-term memory through the Mamba model. Then, we use sub-goals to prompt the transformer, establishing high-quality predictions. Experimental results demonstrate that DM-H achieves state-of-the-art in long and short-term tasks, such as D4RL, Grid World, and Tmaze benchmarks. Regarding efficiency, the online testing of DM-H in the long-term task is 28× times faster than the transformer-based baselines. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Space Representation Learning for Skeleton-based Action Recognition

引用

IEEE Signal Processing Letters 2025年 32卷 2104-2108页

作者： Yang, Yuheng Chen, Haipeng Liu, Zhenguang Hu, Sihao Jiao, Yingying Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Zhejiang University School of Cyber Science and Technology Hangzhou310007 China Georgia Institute of Technology College of Computing GA United States

Skeleton-based action recognition is crucial for machine intelligence. Current methods generally learn from 3D articulated motion sequences in the straightforward Euclidean space. Yet, the vanilla Euclidean space may not be the optimal choice for modeling the intricate correlations among human body joints. This challenge arises from the non-Euclidean nature of human anatomy, where joint correlations often vary non-linearly during movement. To address this, we propose a dual space representation learning method. Specifically, we represent the motion sequences in Hyperbolic space, leveraging its intrinsic properties to capture the non-Euclidean latent anatomy of human motions. We then incorporate the motion features from both Hyperbolic and Euclidean spaces, allowing us to precisely model the non-linear joint correlations while effectively sketching human poses. The proposed method empirically achieves state-of-the-art performance on the NTU RGB+D 60, NTURGB+D 120, and NW-UCLA datasets. © 1994-2012 IEEE.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Attribution rollout: a new way to interpret visual transformer

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第1期14卷 163-173页

作者： Xu, Li Yan, Xin Ding, Weiyue Liu, Zechao College of Computer Science and Technology Harbin Engineering University Nantong Street Heilongjiang Harbin150001 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Street Jilin Changchun130012 China Department of Medicine Harvard Medical School Longwood Avenue BostonMA02115 United States

Transformer-based models are dominating the field of natural language processing and are becoming increasingly popular in the field of computer vision. However, the black box characteristics of transformers seriously hamper their application in certain fields. Prior work relies on the raw attention scores or employs heuristic propagation along with the attention graph. In this work, we propose a new way to visualize model. The method computes attention scores based on attribution and then propagates these attention scores through the layers. This propagation involves attention layers and multi-head attention mechanism. Our method extracts salient dependencies in each layer to visualize prediction results. We benchmark our method on recent visual transformer networks and demonstrate its many advantages over the existing interpretability methods. Our code is available at: https://***/yxheartipp/attr-rollout. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training

arXiv

引用

arXiv 2024年

作者： Liu, Yonghao Li, Mengyu Li, Ximing Huang, Lan Giunchiglia, Fausto Liang, Yanchun Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China University of Trento Trento Italy Zhuhai Laboratory of the Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Zhuhai College of Science and Technology Zhuhai China

Node classification is an essential problem in graph learning. However, many models typically obtain unsatisfactory performance when applied to few-shot scenarios. Some studies have attempted to combine meta-learning with graph neural networks to solve few-shot node classification on graphs. Despite their promising performance, some limitations remain. First, they employ the node encoding mechanism of homophilic graphs to learn node embeddings, even in heterophilic graphs. Second, existing models based on meta-learning ignore the interference of randomness in the learning process. Third, they are trained using only limited labeled nodes within the specific task, without explicitly utilizing numerous unlabeled nodes. Finally, they treat almost all sampled tasks equally without customizing them for their uniqueness. To address these issues, we propose a novel framework for few-shot node classification called Meta-GPS++. Specifically, we first adopt an efficient method to learn discriminative node representations on homophilic and heterophilic graphs. Then, we leverage a prototype-based approach to initialize parameters and contrastive learning for regularizing the distribution of node embeddings. Moreover, we apply self-training to extract valuable information from unlabeled nodes. Additionally, we adopt S2 (scaling & shifting) transformation to learn transferable knowledge from diverse tasks. The results on real-world datasets show the superiority of Meta-GPS++. Our code is available here. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Tasks Benefit Skeleton-based Action Recognition

Auxiliary Tasks Benefit Skeleton-based Action Recognition

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yuheng Yang Haipeng Chen College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Skeleton-based action recognition has long been a fundamental and intriguing problem in machine intelligence. This task is challenging due to pose occlusion and rapid motion, which typically results in incomplete or noisy skeleton data. State-of-the-art methods tend to learn human motion directly from these corrupted skeletons as if they were reliable. Unfortunately, this might lead to unsatisfactory results when key regions of the skeleton are occluded or disturbed. To tackle the problem, we propose a novel framework that integrates auxiliary tasks into a motion modeling network. These auxiliary tasks corrupt partial human skeletons with masking or noise and then force the network to recover the corrupted data, explicitly facilitating robust feature representation learning. We further propose supervising the auxiliary tasks with mutual information losses, mathematically ensuring feature consistency and spatial alignment between the recovered and original skeleton data. Empirically, our approach sets the new state-of-the-art performance on three benchmark datasets.

关键词： Representation learning Noise Speech recognition Benchmark testing Skeleton Mathematical models Reliability Noise measurement Speech processing Mutual information

来源：评论

学校读者我要写书评

暂无评论

Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations

arXiv

引用

arXiv 2023年

作者： Ouyang, Jihong Yang, Zhiyao Liang, Silong Wang, Bing Wang, Yimeng Li, Ximing College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of MOE Jilin University China

Aspect-based sentiment analysis (ABSA), a fine-grained sentiment classification task, has received much attention recently. Many works investigate sentiment information through opinion words, such as "good" and "bad". However, implicit sentiment data widely exists in the ABSA dataset, whose sentiment polarity is hard to determine due to the lack of distinct opinion words. To deal with implicit sentiment, this paper proposes an ABSA method that integrates explicit sentiment augmentations (ABSA-ESA) to add more sentiment clues. We propose an ABSA-specific explicit sentiment generation method to create such augmentations. Specifically, we post-train T5 by rule-based data and employ three strategies to constrain the sentiment polarity and aspect term of the generated augmentations. We employ Syntax Distance Weighting and Unlikelihood Contrastive Regularization in the training procedure to guide the model to generate the explicit opinion words with the same polarity as the input sentence. Meanwhile, we utilize the Constrained Beam Search to ensure the augmentations are aspect-related. We test ABSA-ESA on two ABSA benchmarks. The results show that ABSA-ESA outperforms the SOTA baselines on implicit and explicit sentiment accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Structure-Based Uncertainty Estimation for Source-Free Active Domain Adaptation

引用

IET Computer Vision 2025年第1期19卷

作者： Ouyang, Jihong Zhang, Zhengjie Meng, Qingyi Chi, Jinjin 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

Active domain adaptation (active DA) provides an effective solution by selectively labelling a limited number of target samples to significantly enhance adaptation performance. However, existing active DA methods often struggle in real-world scenarios where, due to data privacy concerns, only a pre-trained source model is available, rather than the source samples. To address this issue, we propose a novel method called the structure-based uncertainty estimation model (SUEM) for source-free active domain adaptation (SFADA). To be specific, we introduce an innovative active sample selection strategy that combines both uncertainty and diversity sampling to identify the most informative samples. We assess the uncertainty in target samples using structure-wise probabilities and implement a diversity selection method to minimise redundancy. For the selected samples, we not only apply standard-supervised loss but also conduct interpolation consistency training to further explore the structural information of the target domain. Extensive experiments across four widely used datasets demonstrate that our method is comparable to or outperforms current UDA and active DA methods. © 2025 The Author(s). IET Computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： computer vision convolutional neural nets image classification

来源：评论

学校读者我要写书评

暂无评论

Improving Local Search for Pseudo Boolean Optimization by Fragile Scoring Function and Deep Optimization 29

Improving Local Search for Pseudo Boolean Optimization by Fr...

引用

29th International Conference on Principles and Practice of Constraint Programming, CP 2023

作者： Zhou, Wenbo Zhao, Yujiao Wang, Yiyuan Cai, Shaowei Wang, Shimao Wang, Xinyu Yin, Minghao School of Information Science and Technology Northeast Normal University Changchun China Key Laboratory of Applied Statistics of MOE Northeast Normal University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of MOE Jilin University Changchun China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783959773003

Pseudo-Boolean optimization (PBO) is usually used to model combinatorial optimization problems, especially for some real-world applications. Despite its significant importance in both theory and applications, there are few works on using local search to solve PBO. This paper develops a novel local search framework for PBO, which has three main ideas. First, we design a two-level selection strategy to evaluate all candidate variables. Second, we propose a novel deep optimization strategy to disturb some search spaces. Third, a sampling flipping method is applied to help the algorithm jump out of local optimum. Experimental results show that the proposed algorithms outperform three state-of-the-art PBO algorithms on most instances. © Wenbo Zhou, Yujiao Zhao, Yiyuan Wang, Shaowei Cai, Shimao Wang, Xinyu Wang, and Minghao Yin.

关键词： Combinatorial optimization

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：