检索结果-内蒙古大学图书馆

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Zhou, Junkai Pang, Liang Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Security Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761193

The emergence of large language models (LLMs) further improves the capabilities of open-domain dialogue systems and can generate fluent, coherent, and diverse responses. However, LLMs still lack a crucial ability: communication skills. This limitation renders them more like information seeking tools rather than anthropomorphic chatbots. Communication skills, such as topic transition, proactively asking questions, concept guidance, empathy, and summarising often should be taken into consideration, to make LLMs more anthropomorphic and proactive during the conversation, thereby increasing the interest of users and attracting them to chat for longer. However, enabling these communication skills in black-box LLMs remains a key challenge because they do not have the same utterance formation mode as real people: think before speaking. Inspired by linguistics and cognitive science, we empower LLMs with communication skills through inner monologues. To evaluate various communication skills, we construct a benchmark named Cskills, which can also more comprehensively evaluate the dialogue generation ability of the model. Experimental results show that the proposed CSIM strategy improves the backbone models and outperforms the baselines. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Understanding and improving adversarial collaborative filtering for robust recommendation 24

Understanding and improving adversarial collaborative filter...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Kaike Zhang Qi Cao Yunfan Wu Fei Sun Huawei Shen Xueqi Cheng CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Beijing China CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences

ISBN: (纸本)9798331314385

Adversarial Collaborative Filtering (ACF), which typically applies adversarial perturbations at user and item embeddings through adversarial training, is widely recognized as an effective strategy for enhancing the robustness of Collaborative Filtering (CF) recommender systems against poisoning attacks. Besides, numerous studies have empirically shown that ACF can also improve recommendation performance compared to traditional CF. Despite these empirical successes, the theoretical understanding of ACF's effectiveness in terms of both performance and robustness remains unclear. To bridge this gap, in this paper, we first theoretically show that ACF can achieve a lower recommendation error compared to traditional CF with the same training epochs in both clean and poisoned data contexts. Furthermore, by establishing bounds for reductions in recommendation error during ACF's optimization process, we find that applying personalized magnitudes of perturbation for different users based on their embedding scales can further improve ACF's effectiveness. Building on these theoretical understandings, we propose Personalized Magnitude Adversarial Collaborative Filtering (PamaCF). Extensive experiments demonstrate that PamaCF effectively defends against various types of poisoning attacks while significantly enhancing recommendation performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CausalDiff: causality-inspired disentanglement via diffusion model for adversarial defense 24

CausalDiff: causality-inspired disentanglement via diffusion...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Mingkun Zhang Keping Bi Wei Chen Quanrun Chen Jiafeng Guo Xueqi Cheng CAS Key Laboratory of AI Safety Institute of Computing Technology CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology CAS School of Statistics University of International Business and Economics

ISBN: (纸本)9798331314385

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://***/cas-aisafetyBasicResearchGroup/CausalDiff.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion 38

PDE+: Enhancing Generalization via PDE with Adaptive Distrib...

引用

38th AAai Conference on Artificial Intelligence, AAai 2024

作者： Yuan, Yige Xu, Bingbing Lin, Bo Hou, Liang Sun, Fei Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety & Security Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Mathematics National University of Singapore Singapore

ISBN: (纸本)1577358872

The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones. Current methods, mainly based on the data-driven paradigm such as data augmentation, adversarial training, and noise injection, may encounter limited generalization due to model non-smoothness. In this paper, we propose to investigate generalization from a Partial Differential Equation (PDE) perspective, aiming to enhance it directly through the underlying function of neural networks, rather than focusing on adjusting input data. Specifically, we first establish the connection between neural network generalization and the smoothness of the solution to a specific PDE, namely transport equation. Building upon this, we propose a general framework that introduces adaptive distributional diffusion into transport equation to enhance the smoothness of its solution, thereby improving generalization. In the context of neural networks, we put this theoretical framework into practice as PDE+ (PDE with Adaptive Distributional Diffusion) which diffuses each sample into a distribution covering semantically similar inputs. This enables better coverage of potentially unobserved distributions in training, thus improving generalization beyond merely data-driven methods. The effectiveness of PDE+ is validated through extensive experimental settings, demonstrating its superior performance compared to state-of-the-art methods. Our code is available at https://***/yuanyige/pde-add. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Personalized Denoising Implicit Feedback for Robust Recommender System

arXiv

引用

arXiv 2025年

作者： Zhang, Kaike Cao, Qi Wu, Yunfan Sun, Fei Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China

While implicit feedback is foundational to modern recommender systems, factors such as human error, uncertainty, and ambiguity in user behavior inevitably introduce significant noise into this feedback, adversely affecting the accuracy and robustness of recommendations. To address this issue, existing methods typically aim to reduce the training weight of noisy feedback or discard it entirely, based on the observation that noisy interactions often exhibit higher losses in the overall loss distribution. However, we identify two key issues: (1) there is a significant overlap between normal and noisy interactions in the overall loss distribution, and (2) this overlap becomes even more pronounced when transitioning from pointwise loss functions (e.g., BCE loss) to pairwise loss functions (e.g., BPR loss). This overlap leads traditional methods to misclassify noisy interactions as normal, and vice versa. To tackle these challenges, we further investigate the loss overlap and find that for a given user, there is a clear distinction between normal and noisy interactions in the user’s personal loss distribution. Based on this insight, we propose a resampling strategy to Denoise using the user’s Personal Loss distribution, named PLD, which reduces the probability of noisy interactions being optimized. Specifically, during each optimization iteration, we create a candidate item pool for each user and resample the items from this pool based on the user’s personal loss distribution, prioritizing normal interactions. Additionally, we conduct a theoretical analysis to validate PLD’s effectiveness and suggest ways to further enhance its performance. Extensive experiments conducted on three datasets with varying noise ratios demonstrate PLD’s efficacy and robustness. Copyright © 2025, The Authors. All rights reserved.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Enhancing Stance Detection on Social Media via Core Views Discovery 27

Enhancing Stance Detection on Social Media via Core Views Di...

引用

27th European Conference on Artificial Intelligence, ECai 2024

作者： Yan, Yu Shen, Yinghan Liu, Teli Jiang, Xuhui Yin, Dechun School of Information and Network Security People Public Security University of China China Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9781643685489

Stance detection aims to identify the expressed attitude towards a target from the text, which is significant for learning public cognition from social media. The short and implicit nature of social media users' expressions potentially results in the stance understanding bias of the model. To address this problem, introducing external background information is helpful to mitigate these biases and enhance explainability. The core view, reflecting the motivations and reasons behind an individual's stance toward the target, can be summarized and extracted from collective tweets, which can serve as a reference for stance detection. In this study, we propose the Stance Detection via Core View Discovery (SD-CVM), where the core views are used for background information modeling. Specifically, we construct a joint classifier combining the semantic understanding of tweets and their relevant core views from the public. We utilize the Large Language Model (LLM) to extract core views with stances from tweets and use these core views as background references for tweets. To further optimize the tweet understanding, we develop the contrastive and rebalancing mechanism by incorporating stance supervision signals for training. Experiments on two representative datasets demonstrate the excellent performance of our method. © 2024 The Authors.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Evaluation of In-Context Learning for LLMs

Rethinking the Evaluation of In-Context Learning for LLMs

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yu, Guoxin Liu, Lemao Yu, Mo Yu, Yue Ao, Xiang Institute of Computing Technology CAS Beijing100190 China Peng Cheng Laboratory Shenzhen China University of Chinese Academy of Sciences Beijing100049 China Wechat AI Tencent China Key Lab of AI Safety Chinese Academy of Sciences Beijing100094 China

ISBN: (纸本)9798891761643

In-context learning (ICL) has demonstrated excellent performance across various downstream NLP tasks, especially when synergized with powerful large language models (LLMs). Existing studies evaluate ICL methods primarily based on downstream task performance. This evaluation protocol overlooks the significant cost associated with the demonstration configuration process, i.e., tuning the demonstration as the ICL prompt. However, in this work, we point out that the evaluation protocol leads to unfair comparisons and potentially biased evaluation, because we surprisingly find the correlation between the configuration costs and task performance. Then we call for a two-dimensional evaluation paradigm that considers both of these aspects, facilitating a fairer comparison. Finally, based on our empirical finding that the optimized demonstration on one language model generalizes across language models of different sizes, we introduce a simple yet efficient strategy that can be applied to any ICL method as a plugin, yielding a better trade-off between the two dimensions according to the proposed evaluation paradigm. © 2024 Association for Computational Linguistics.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Confidence Aware Learning for Reliable Face Anti-spoofing

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5083-5093页

作者： Long, Xingming Zhang, Jie Shan, Shiguang Key Laboratory of AI Safety of CAS Institute of Computing Technology (ICT) Chinese Academy of Sciences (CAS) Beijing China University of Chinese Academy of Sciences (UCAS) Beijing China

Current Face Anti-spoofing (FAS) models tend to make overly confident predictions even when encountering unfamiliar scenarios or unknown presentation attacks, which leads to serious potential risks. To solve this problem, we propose a Confidence Aware Face Anti-spoofing (CA-FAS) model, which is aware of its capability boundary, thus achieving reliable liveness detection within this boundary. To enable the CA-FAS to "know what it doesn’t know", we propose to estimate its confidence during the prediction of each sample. Specifically, we build Gaussian distributions for both the live faces and the known attacks. The prediction confidence for each sample is subsequently assessed using the Mahalanobis distance between the sample and the Gaussians for the "known data". We further introduce the Mahalanobis distance-based triplet mining to optimize the parameters of both the model and the constructed Gaussians as a whole. Extensive experiments show that the proposed CA-FAS can effectively recognize samples with low prediction confidence and thus achieve much more reliable performance than other FAS models by filtering out samples that are beyond its reliable range. © 2005-2012 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

GNN-Based Persistent K-core Community Search in Temporal Graphs

GNN-Based Persistent K-core Community Search in Temporal Gra...

引用

IEEE International Conference on Big Data

作者： Zongli Jiang Yirui Tan Guoxin Chen Fangda Guo Jinli Zhang Xiaolu Bai Computer Science and Technology Beijing University of Technology Beijing China Key Laboratory of AI Safety Institute of Computing Technology CAS University of Chinese Academy of Sciences Beijing China Key Laboratory of AI Safety Institute of Computing Technology CAS Beijing China

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

The goal of community search is to provide effective solutions for real-time, high-quality community searches within large networks. In many practical applications, such as event organization and friend recommendations, discovering various community structures within a network is crucial for users. However, existing community search algorithms rarely address issues within temporal graphs, and those that do often have two main limitations: (1) traditional community search methods become inefficient and experience significant increases in computation time when scaled to large graphs; (2) while GNN-based community search methods for temporal graphs offer generalizability, they often focus solely on community connectivity and lack cohesiveness. Therefore, we propose a new model PK-GCN, based on Graph Neural Networks (GNNs), to identify persistent k-core communities in temporal networks. This model can handle dynamic changes in temporal graphs and identify communities that persist over time. Compared to existing community search methods, our model not only finds communities with tighter structures but also allows for dynamic queries based on user input without needing retraining. Specifically, our model constructs features by integrating k-core information from core decomposition, graph features, and query features, resulting in more expressive node representations. Additionally, we designed a flexible dynamic query mechanism that allows users to input time information to query communities. Experiments on multiple datasets demonstrate that our model outperforms other GNN-based community search algorithms in F1-score.

关键词： Computational modeling Heuristic algorithms Organizations Big Data Benchmark testing Search problems Graph neural networks Data models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning

arXiv

引用

arXiv 2024年

作者： Wang, Zixu Xu, Bingbing Yuan, Yige Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China

Graph contrastive learning (GCL), standing as the dominant paradigm in the realm of graph pre-training, has yielded considerable progress. Nonetheless, its capacity for out-of-distribution (OOD) generalization has been relatively underexplored. In this work, we point out that the traditional optimization of InfoNCE in GCL restricts the cross-domain pairs only to be negative samples, which inevitably enlarges the distribution gap between different domains. This violates the requirement of domain invariance under OOD scenario and consequently impairs the model’s OOD generalization performance. To address this issue, we propose a novel strategy "Negative as Positive", where the most semantically similar cross-domain negative pairs are treated as positive during GCL. Our experimental results, spanning a wide array of datasets, confirm that this method substantially improves the OOD generalization performance of GCL. © 2024, CC BY.

关键词：

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：