检索结果-内蒙古大学图书馆

Disentangled Graph Representation with Contrastive Learning for Rumor Detection

学校读者我要写书评

暂无评论

Disentangled Graph Representation with Contrastive Learning ...

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

作者： Haoyu Liu Yuanhai Xue Xiaoming Yu CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences

With many social problems nowadays, rumor detection in social media has become increasingly important. Previous works proposed classical and deep learning methods to extract information from features or rumor propagation structures. However, these methods either require lots of labeled data or are disturbed by noise nodes easily. To address these challenges, we propose a novel method that Disentangles graph representations with Contrastive learning for Rumor Detection (DCRD). Specifically, we design a graph contrastive learning strategy, significantly reducing the requirement of labeled data. We disentangle attention and redundant graph representations to extract intrinsic features and exclude the influence of redundant information. In addition, we utilize the disentangled two parts as hard negative samples to enhance contrastive learning further. Experiment results on two real-world datasets show that DCRD outperforms state-of-the-art models. More validation experiments demonstrate the data efficiency and robustness of our method.

关键词：

Rethinking the evaluation of out-of-distribution detection: a sorites paradox 24

学校读者我要写书评

暂无评论

Rethinking the evaluation of out-of-distribution detection: ...

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

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

ISBN: (纸本)9798331314385

Most existing out-of-distribution (OOD) detection benchmarks classify samples with novel labels as the OOD data. However, some marginal OOD samples actually have close semantic contents to the in-distribution (ID) sample, which makes determining the OOD sample a Sorites Paradox. In this paper, we construct a benchmark named Incremental Shift OOD (IS-OOD) to address the issue, in which we divide the test samples into subsets with different semantic and covariate shift degrees relative to the ID dataset. The data division is achieved through a shift measuring method based on our proposed Language Aligned Image feature Decomposition (LaiD). Moreover, we construct a Synthetic Incremental Shift (Syn-IS) dataset that contains high-quality generated images with more diverse covariate contents to complement the IS-OOD benchmark. We evaluate current OOD detection methods on our benchmark and find several important insights: (1) The performance of most OOD detection methods significantly improves as the semantic shift increases; (2) Some methods like GradNorm may have different OOD detection mechanisms as they rely less on semantic shifts to make decisions; (3) Excessive covariate shifts in the image are also likely to be considered as OOD for some methods. Our code and data are released in https://***/qqwsad5/IS-OOD.

关键词：

TEA: Test-Time Energy Adaptation

学校读者我要写书评

暂无评论

TEA: Test-Time Energy Adaptation

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yige Yuan Bingbing Xu Liang Hou Fei Sun Huawei Shen Xueqi Cheng CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Kuaishou Technology

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Test Time Adaptation (TTA) aims to improve model generalizability when test data diverges from training distribution, with the distinct advantage of not requiring access to training data and processes, especially valuable in the context of pre-trained models. However, current TTA methods fail to address the fundamental issue: covariate shift, i. e., the decreased generalizability can be attributed to the model's reliance on the marginal distribution of the training data, which may impair model calibration and introduce confirmation bias. To address this, we propose a novel energy-based perspective, enhancing the model's perception of target data distributions without requiring access to training data or processes. Building on this perspective, we introduce Test-time Energy Adaptation (TEA), which transforms the trained classifier into an energy-based model and aligns the model's distribution with the test data's, enhancing its ability to perceive test distributions and thus improving overall generalizability. Extensive experiments across multiple tasks, benchmarks and architectures demonstrate TEA's superior generalization performance against state-of-the-art methods. Further in-depth analyses reveal that TEA can equip the model with a comprehensive perception of test distribution, ultimately paving the way toward improved generalization and calibration 1 1 Code is available at https://***/yuanyige/tea

关键词： Training Adaptation models Analytical models Training data Computer architecture Transforms Benchmark testing

Precise Integral in NeRFs: Overcoming the Approximation Errors of Numerical Quadrature

学校读者我要写书评

暂无评论

Precise Integral in NeRFs: Overcoming the Approximation Erro...

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Boyuan Zhang Zhenliang He Meina Kan Shiguang Shan Key Lab of AI Safety Institute of Computing Technology CAS China University of Chinese Academy of Sciences China

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Neural Radiance Fields (NeRFs) use neural networks to translate spatial coordinates to corresponding volume density and directional radiance, enabling realistic novel view synthesis through volume rendering. Rendering new viewpoints involves computing volume rendering integrals along rays, usually approximated by numerical quadrature because of lacking closed-form solutions. In this paper, utilizing Taylor expansion, we demonstrate that numerical quadrature causes inevitable approximation error in NeRF integrals due to ignoring the parameter associated with the Lagrange remainder. To mitigate the approximation error, we propose a novel neural field with segment representation as input to implicitly model the remainder parameter. In theory, our proposed method is proven to possess the potential to achieve fully precise rendering integral, as demonstrated by comprehensive experiments on several commonly used datasets with state-of-the-art results.

关键词： Training Geometry Computer vision Closed-form solutions Neural networks Neural radiance field Approximation error Rendering (computer graphics) Taylor series Numerical models

Understanding the Collapse of LLMs in Model Editing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Wanli Sun, Fei Tan, Jiajun Ma, Xinyu Su, Du Yin, Dawei Shen, Huawei CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China University of Chinese Academy of Sciences China Baidu Inc. China

Despite significant progress in model editing methods, their application in real-world scenarios remains challenging as they often cause large language models (LLMs) to collapse. Among them, ROME is particularly concerning, as it could disrupt LLMs with only a single edit. In this paper, we study the root causes of such collapse. Through extensive analysis, we identify two primary factors that contribute to the collapse: i) inconsistent handling of prefixed and unprefixed keys in the parameter update equation may result in very small denominators, causing excessively large parameter updates;ii) the subject of collapse cases is usually the first token, whose unprefixed key distribution significantly differs from the prefixed key distribution in autoregressive transformers, causing the aforementioned issue to materialize. To validate our findings, we propose a simple yet effective approach: uniformly using prefixed keys during editing phase and adding prefixes during testing phase to ensure the consistency between training and testing. The experimental results show that the proposed solution can prevent model collapse while maintaining the effectiveness of the edits1 Copyright © 2024, The Authors. All rights reserved.

关键词： Distribution transformers

Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Kangxi Pang, Liang Shen, Huawei Cheng, Xueqi Key Laboratory of AI Safety Chinese Academy of Sciences Institute of Computing Technology CAS China University of Chinese Academy of Sciences China

The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) methods are considered effective solutions to address these challenges. Most recent TDA methods rely on influence functions, assuming the model achieves minimized empirical risk. However, achieving this criterion is difficult, and sourcing accuracy can be compromised by fitting errors during model training. In this paper, we introduce a novel TDA method called Debias and Denoise Attribution (DDA), which enhances influence functions by addressing fitting errors. Specifically, the debias strategy seeks to improve the performance of influence functions by eliminating the knowledge bias present in the base model before fine-tuning, while the denoise strategy aims to reduce discrepancies in influence scores arising from varying degrees of fitting during the training process through smoothing techniques. Experimental results demonstrate that our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. Moreover, DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral. 1 © 2024, CC BY.

关键词： Digital elevation model

Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hou, Danyang Pang, Liang 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

Video Corpus Moment Retrieval (VCMR) is a new video retrieval task aimed at retrieving a relevant moment from a large corpus of untrimmed videos using a text query. The relevance between the video and query is partial, mainly evident in two aspects: (1) Scope: The untrimmed video contains many frames, but not all are relevant to the query. Strong relevance is typically observed only within the relevant moment. (2) Modality: The relevance of the query varies with different modalities. Action descriptions align more with visual elements, while character conversations are more related to textual information. Existing methods often treat all video contents equally, leading to sub-optimal moment retrieval. We argue that effectively capturing the partial relevance between the query and video is essential for the VCMR task. To this end, we propose a Partial Relevance Enhanced Model (PREM) to improve VCMR. VCMR involves two sub-tasks: video retrieval and moment localization. To align with their distinct objectives, we implement specialized partial relevance enhancement strategies. For video retrieval, we introduce a multi-modal collaborative video retriever, generating different query representations for the two modalities by modality-specific pooling, ensuring a more effective match. For moment localization, we propose the focus-then-fuse moment localizer, utilizing modality-specific gates to capture essential content. We also introduce relevant content-enhanced training methods for both retriever and localizer to enhance the ability of model to capture relevant content. Experimental results on TVR and DiDeMo datasets show that the proposed model outperforms the baselines, achieving a new state-of-the-art of VCMR. The code is available at https://***/hdy007007/PREM. © 2024, CC BY.

关键词：

ALiiCE: Evaluating Positional Fine-grained Citation Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Yilong Gao, Jinhua Yu, Xiaoming Bi, Baolong Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Large Language Model (LLM) can enhance its credibility and verifiability by generating text with citations. However, existing research on citation generation is predominantly limited to sentence-level statements, neglecting the significance of positional fine-grained citations that can appear anywhere within sentences. To facilitate further exploration of the positional fine-grained citation generation, we propose ALiiCE, the first automatic evaluation framework for this task. Our method employs a dependency tree based approach to parse the sentence-level claim into atomic claims. Then ALiiCE evaluates citation quality using three metrics, including positional fine-grained citation recall, precision, and coefficient of variation of citation positions. We evaluate the positional fine-grained citation generation performance of several LLMs on long-form QA datasets. Our experiments and analyses demonstrate the effectiveness and reasonableness of ALiiCE. We offer our insights into the current advancements and future directions for the positional fine-grained citation generation task. Copyright © 2024, The Authors. All rights reserved.

关键词： Modeling languages

M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Song, Wei Li, Yadong Xu, Jianhua Wu, Guowei Ming, Lingfeng Yi, Kexin Luo, Weihua Li, Houyi Du, Yi Guo, Fangda Yu, Kaicheng AutoLab Westlake University China AI Business Alibaba Group China Zhejiang University China Key Laboratory of Behavioral Science Institute of Psychology CAS China Key Laboratory of AI Safety Institute of Computing Technology CAS China

As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human intelligence. However, existing benchmarks mainly focus on evaluating solely on task performance, such as the accuracy of identifying the attribute of an object. Combining well-developed cognitive science to understand the intelligence of MLLMs beyond superficial achievements remains largely unexplored. To this end, we introduce the first cognitive-driven multi-lingual and multi-modal benchmark to evaluate the general intelligence ability of MLLMs, dubbed M3GIA. Specifically, we identify five key cognitive factors based on the well-recognized Cattell-Horn-Carrol (CHC) model of intelligence and propose a novel evaluation metric. In addition, since most MLLMs are trained to perform in different languages, a natural question arises: is language a key factor influencing the cognitive ability of MLLMs? As such, we go beyond English to encompass other languages based on their popularity, including Chinese, French, Spanish, Portuguese and Korean, to construct our M3GIA. We make sure all the data relevant to the cultural backgrounds are collected from their native context to avoid English-centric bias. We collected a significant corpus of data from human participants, revealing that the most advanced MLLM reaches the lower boundary of human intelligence in English. Yet, there remains a pronounced disparity in the other five languages assessed. We also reveals an interesting winner takes all phenomenon that are aligned with the discovery in cognitive studies. Our benchmark will be open-sourced, with the aspiration of facilitating the enhancement of cognitive capabilities in MLLMs. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking