检索结果-内蒙古大学图书馆

Regularizing Hard Examples Improves Adversarial Robustness

JOURNAL OF MACHINE LEARNING RESEARCH 2025年 26卷

作者： Lee, Hyungyu Lee, Saehyung Bae, Ho Yoon, Sungroh Seoul Natl Univ Elect & Comp Engn Interdisciplinary Program Artificial Intelligence Seoul 08826 South Korea Ewha Womans Univ Dept Cyber Secur Seoul 03760 South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Elect & Comp Engn AIISASRIINMC Seoul 08826 South Korea Seoul Natl Univ ISRC Seoul 08826 South Korea

Recent studies have validated that pruning hard-to-learn examples from training improves the generalization performance of neural networks (NNs). In this study, we investigate this intriguing phenomenon-the negative effect of hard examples on generalization-in adversarial training. Particularly, we theoretically demonstrate that the increase in the difficulty of hard examples in adversarial training is significantly greater than the increase in the difficulty of easy examples. Furthermore, we verify that hard examples are only fitted through memorization of the label in adversarial training. We conduct both theoretical and empirical analyses of this memorization phenomenon, showing that pruning hard examples in adversarial training can enhance the model's robustness. However, the challenge remains in finding the optimal threshold for removing hard examples that degrade robustness performance. Based upon these observations, we propose a new approach, difficulty proportional label smoothing (DPLS), to adaptively mitigate the negative effect of hard examples, thereby improving the adversarial robustness of NNs. Notably, our experimental result indicates that our method can successfully leverage hard examples while circumventing the negative effect.

关键词： adversarial robustness adversarial examples hard examples memorization robust overfitting

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges

引用

artificial intelligence REVIEW 2025年第7期58卷 1-95页

作者： Kim, Jongseon Kim, Hyungjoon Kim, Hyungi Lee, Dongjun Yoon, Sungroh Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea Seoul Natl Univ AIIS ASRI Seoul South Korea Seoul Natl Univ INMC Seoul South Korea R&D Dept LG Chem Seoul South Korea Samsung SDI R&D Dept Yongin South Korea

Time series forecasting is a critical task that provides key information for decision-making across various fields, such as economic planning, supply chain management, and medical diagnosis. After the use of traditional statistical methodologies and machine learning in the past, various fundamental deep learning architectures such as MLPs, CNNs, RNNs, and GNNs have been developed and applied to solve time series forecasting problems. However, the structural limitations caused by the inductive biases of each deep learning architecture constrained their performance. Transformer models, which excel at handling long-term dependencies, have become significant architectural components for time series forecasting. However, recent research has shown that alternatives such as simple linear layers can outperform Transformers. These findings have opened up new possibilities for using diverse architectures, ranging from fundamental deep learning models to emerging architectures and hybrid approaches. In this context of exploration into various models, the architectural modeling of time series forecasting has now entered a renaissance. This survey not only provides a historical context for time series forecasting but also offers comprehensive and timely analysis of the movement toward architectural diversification. By comparing and re-examining various deep learning models, we uncover new perspectives and present the latest trends in time series forecasting, including the emergence of hybrid models, diffusion models, Mamba models, and foundation models. By focusing on the inherent characteristics of time series data, we also address open challenges that have gained attention in time series forecasting, such as channel dependency, distribution shift, causality, and feature extraction. This survey explores vital elements that can enhance forecasting performance through diverse approaches. These contributions help lower entry barriers for newcomers by providing a systematic underst

关键词： Time series forecasting Deep learning Foundation model Distribution shift Causality

来源：评论

学校读者我要写书评

暂无评论

Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation

arXiv

引用

arXiv 2025年

作者： Kim, HyunGi Kim, Siwon Mok, Jisoo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of AIIS ASRI INMC Seoul National University Korea Republic of

Deep Neural Networks have spearheaded remarkable advancements in time series forecasting (TSF), one of the major tasks in time series modeling. Nonetheless, the non-stationarity of time series undermines the reliability of pre-trained source time series forecasters in mission-critical deployment settings. In this study, we introduce a pioneering test-time adaptation framework tailored for TSF (TSF-TTA). TAFAS, the proposed approach to TSF-TTA, flexibly adapts source forecasters to continuously shifting test distributions while preserving the core semantic information learned during pre-training. The novel utilization of partially-observed ground truth and gated calibration module enables proactive, robust, and model-agnostic adaptation of source forecasters. Experiments on diverse benchmark datasets and cutting-edge architectures demonstrate the efficacy and generality of TAFAS, especially in long-term forecasting scenarios that suffer from significant distribution shifts. The code is available at https://***/kimanki/TAFAS. © 2025, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

On Task-Relevant Loss Functions in Meta-Reinforcement Learning 6

On Task-Relevant Loss Functions in Meta-Reinforcement Learni...

引用

6th Annual Learning for Dynamics and Control Conference

作者： Shin, Jaeuk Kim, Giho Lee, Howon Han, Joonho Yang, Insoon Seoul Natl Univ Dept Elect & Comp Engn ASRI Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence ASRI Seoul South Korea

Designing a competent meta-reinforcement learning (meta-RL) algorithm in terms of data usage remains a central challenge to be tackled for its successful real-world applications. In this paper, we propose a sample-efficient meta-RL algorithm that learns a model of the system or environment at hand in a task-directed manner. As opposed to the standard model-based approaches to meta-RL, our method exploits the value information in order to rapidly capture the decision-critical part of the environment. The key component of our method is the loss function for learning both the task inference module and the system model. This systematically couples the model discrepancy and the value estimate, thereby enabling our proposed algorithm to learn the policy and task inference module with a significantly smaller amount of data compared to the existing meta-RL algorithms. The proposed method is evaluated in high-dimensional robotic control, empirically verifying its effectiveness in extracting information indispensable for solving the tasks from observations in a sample-efficient manner.

关键词： Reinforcement learning meta-reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adversarial Environment Design via Regret-Guided Diffusion Models 38

Adversarial Environment Design via Regret-Guided Diffusion M...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chung, Hojun Lee, Junseo Kim, Minsoo Kim, Dohyeong Oh, Songhwai Interdisciplinary Program in Artificial Intelligence ASRI Seoul National University Korea Republic of Department of Electrical and Computer Engineering ASRI Seoul National University Korea Republic of

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://***/projects/ADD. © 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

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORKS 10

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORK...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering AIIS ASRI INMC ISRC NSI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Learning Fair Classifiers with Partially Annotated Group Labels

Learning Fair Classifiers with Partially Annotated Group Lab...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jung, Sangwon Chun, Sanghyuk Moon, Taesup Seoul Natl Univ Dept ECE ASRI Seoul South Korea NAVER AI Lab Seongnam South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Recently, fairness-aware learning have become increasingly crucial, but most of those methods operate by assuming the availability of fully annotated demographic group labels. We emphasize that such assumption is unrealistic for real-world applications since group label annotations are expensive and can conflict with privacy issues. In this paper, we consider a more practical scenario, dubbed as Algorithmic Group Fairness with the Partially annotated Group labels (Fair-PG). We observe that the existing methods to achieve group fairness perform even worse than the vanilla training, which simply uses full data only with target labels, under Fair-PG. To address this problem, we propose a simple Confidence-based Group Label assignment (CGL) strategy that is readily applicable to any fairness-aware learning method. CGL utilizes an auxiliary group classifier to assign pseudo group labels, where random labels are assigned to low confident samples. We first theoretically show that our method design is better than the vanilla pseudo-labeling strategy in terms of fairness criteria. Then, we empirically show on several benchmark datasets that by combining CGL and the state-of-the-art fairness-aware inprocessing methods, the target accuracies and the fairness metrics can be jointly improved compared to the baselines. Furthermore, we convincingly show that CGL enables to naturally augment the given group-labeled dataset with external target label-only datasets so that both accuracy and fairness can be improved Code is available at https://***/naver-ai/cgl_fairness.

关键词： Training Measurement Learning systems Privacy Computer vision Codes Annotations

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Stego: Training-free diffusion generative steganography via message projection

引用

Information Sciences 2025年 718卷

作者： Daegyu Kim Chaehun Shin Jooyoung Choi Dahuin Jung Sungroh Yoon Data Science and AI Laboratory Electrical and Computer Engineering Seoul National University Seoul 08826 Republic of Korea School of Computer Science and Engineering Soongsil University Seoul 06978 Republic of Korea Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul 08826 Republic of Korea AIIS ASRI INMC and ISRC Seoul National University Seoul 08826 Republic of Korea

Generative steganography is the process of hiding secret messages in generated images instead of cover images. Existing studies on generative steganography use GAN or Flow models to obtain high hiding message capacity and anti-detection ability over cover images. However, they create relatively unrealistic stego images because of the inherent limitations of generative models. We propose Diffusion-Stego, a generative steganography approach based on diffusion models that outperform other generative models in image generation. Diffusion-Stego projects secret messages into the latent noise of diffusion models and generates stego images with an iterative denoising process. Since the naive hiding of secret messages into noise boosts visual degradation and decreases extracted message accuracy, we introduce message projection, which hides messages into noise space while addressing these issues. We suggest three options for message projection to adjust the trade-off between extracted message accuracy, anti-detection ability, and image quality. Diffusion-Stego is a training-free approach, so we can apply it to pre-trained diffusion models that generate high-quality images, or even large-scale text-to-image models, such as Stable diffusion. Diffusion-Stego achieved a high capacity of messages as well as high quality that makes it challenging to distinguish from real images in the PNG format.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RNR-Nav: A Real-World Visual Navigation System Using Renderable Neural Radiance Maps

RNR-Nav: A Real-World Visual Navigation System Using Rendera...

引用

2024 International Conference on Intelligent Robots and Systems

作者： Kim, Minsoo Kwon, Obin Jun, Howoong Oh, Songhwai Interdisciplinary Program Artificial Intelligence Seoul South Korea ASRI Seoul South Korea Seoul Natl Univ Dept Elect & Comp Engn ECE Seoul South Korea Sequor Robot Inc Seoul South Korea

ISBN: (纸本)9798350377712;9798350377705

We propose a novel visual localization and navigation framework for real-world environments directly integrating observed visual information into the bird-eye-view map. While the renderable neural radiance map (RNR-Map) [1] shows considerable promise in simulated settings, its deployment in real-world scenarios poses undiscovered challenges. RNR-Map utilizes projections of multiple vectors into a single latent code, resulting in information loss under suboptimal conditions. To address such issues, our enhanced RNR-Map for real-world robots, RNR-Map++, incorporates strategies to mitigate information loss, such as a weighted map and positional encoding. For robust real-time localization, we integrate a particle filter into the correlation-based localization framework using RNR-Map++ without a rendering procedure. Consequently, we establish a real-world robot system for visual navigation utilizing RNR-Map++, which we call "RNR-Nav." Experimental results demonstrate that the proposed methods significantly enhance rendering quality and localization robustness compared to previous approaches. In real-world navigation tasks, RNR-Nav achieves a success rate of 84.4%, marking a 68.8% enhancement over the methods of the original RNR-Map paper.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Branched Regularization for Federated Learning 39

Multi-Level Branched Regularization for Federated Learning

引用

39th International Conference on Machine Learning (ICML)

作者： Kim, Jinkyu Kim, Geeho Han, Bohyung Seoul Natl Univ Dept Elect & Comp Engn Comp Vis Lab Seoul South Korea Seoul Natl Univ ASRI Seoul South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul South Korea

A critical challenge of federated learning is data heterogeneity and imbalance across clients, which leads to inconsistency between local networks and unstable convergence of global models. To alleviate the limitations, we propose a novel architectural regularization technique that constructs multiple auxiliary branches in each local model by grafting local and global subnetworks at several different levels and that learns the representations of the main pathway in the local model congruent to the auxiliary hybrid pathways via online knowledge distillation. The proposed technique is effective to robustify the global model even in the non-iid setting and is applicable to various federated learning frameworks conveniently without incurring extra communication costs. We perform comprehensive empirical studies and demonstrate remarkable performance gains in terms of accuracy and efficiency compared to existing methods. The source code is available in our project page(1).

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：