通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2412.18355cs.CVcs.AIcs.LG
通过 Tail Anchor 处理联邦持续学习中的时空数据异构性
Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor
Southwestern University of Finance and Economics（西南财经大学）；University of Electronic Science and Technology of China（电子科技大学）；WeBank（微众银行）；Southwest Jiaotong University（西南交通大学）；Hong Kong University of Science and Technology（香港科技大学）
Hao Yu, Xin Yang, Le Zhang, Hanlin Gu, Tianrui Li, Lixin Fan, Qiang Yang
Federated continual learning (FCL) allows each client to continually update its knowledge from task streams, enhancing the applicability of federated learning in real-world scenarios. However, FCL needs to address not only spatial data heterogeneity between clients but also temporal data heterogeneity between tasks. In this paper, empirical experiments demonstrate that such input-level heterogeneity significantly affects the model's internal parameters and outputs, leading to severe spatial-temporal catastrophic forgetting of local and previous knowledge. To this end, we propose Federated Tail Anchor (FedTA) to mix trainable Tail Anchor with the frozen output features to adjust their position in the feature space, thereby overcoming parameter-forgetting and output-forgetting. Three novel components are also included: Input Enhancement for improving the performance of pre-trained models on downstream tasks; Selective Input Knowledge Fusion for fusion of heterogeneous local knowledge on the server; and Best Global Prototype Selection for finding the best anchor point for each class in the feature space. Extensive experiments demonstrate that FedTA not only outperforms existing FCL methods but also effectively preserves the relative positions of features.
In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forget previously acquired knowledge. To address such catastrophic forgetting, many continual learning methods implement different types of experience replay, re-learning on past data stored in a small buffer known as episodic memory. In this work, we complement experience replay with a new objective that we call anchoring, where the learner uses bilevel optimization to update its knowledge on the current task, while keep…
From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity
School of Software, Shandong University（山东大学软件学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）
Dynamically Anchored Prompting for Task-Imbalanced Continual Learning
Xiamen University（厦门大学）；Univ. Grenoble Alpes（格勒诺布尔大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）；LJK（让·昆廷诺实验室）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））
Department of Computer Science and Technology, Tsinghua University, China（计算机科学与技术系，清华大学，中国）；College of Computer Science, Zhejiang University, China（浙江大学计算机科学学院，中国）；College of Computer Science, Beijing University of Posts and Telecommunications, China（北京邮电大学计算机科学学院，中国）
本文提出连续GUI代理任务，通过引入GUI-Anchoring in Flux框架，解决GUI分布变化时持续学习稳定性问题，实验显示其优于现有方法。
Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings
Department of Computer Science, Iowa State University（爱荷华州立大学计算机科学系）；Department of Computer Science & Engineering, BRAC University（BRAC大学计算机科学与工程系）；Department of Civil, Construction & Environmental Engineering, Iowa State University（爱荷华州立大学土木、建设与环境工程系）
Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors
School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；Data61, CSIRO（CSIRO数据61研究中心）；School of Computer Science, University of Auckland（奥克兰大学计算机科学学院）；Australian Institute for Machine Learning (AIML), The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）
We study the relationship between catastrophic forgetting and properties of task sequences. In particular, given a sequence of tasks, we would like to understand which properties of this sequence influence the error rates of continual learning algorithms trained on the sequence. To this end, we propose a new procedure that makes use of recent developments in task space modeling as well as correlation analysis to specify and analyze the properties we are interested in. As an application, we apply our procedure to study two properties of a task sequence: (1) total complexity and (2) sequential h…
Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era
Shenzhen Graduate School of Peking University（北京大学深圳研究生院）；Centre for Artificial Intelligence and Robotics, HKISI, CAS（香港科学院人工智能与机器人研究中心）；Peng Cheng Laboratory（鹏城实验室）
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Computer Vision Center, Barcelona University of Chinese Academy of Sciences（巴塞罗那大学计算机视觉中心，中国科学院）；State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所机器人学国家重点实验室）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造研究所）
Federated Continual Learning: Concepts, Challenges, and Solutions
Faculty of Computer Science, University of New Brunswick（新 Brunswick大学计算机科学学院）；Department of Electrical and Computer Engineering, University of Windsor（温莎大学电气与计算机工程系）
AFCL: Analytic Federated Continual Learning for Spatio-Temporal Invariance of Non-IID Data
Peking University, China（北京大学）；South China University of Technology, China（华南理工大学）；Central South University, China（中南大学）；Beijing Normal University, China（北京师范大学）；University of Southampton, UK（南安普顿大学）；University of Maryland, Baltimore County, USA（马里兰大学巴尔的摩县分校）
Adapting model parameters to incoming streams of data is a crucial factor to deep learning scalability. Interestingly, prior continual learning strategies in online settings inadvertently anchor their updated parameters to a local parameter subspace to remember old tasks, else drift away from the subspace and forget. From this observation, we formulate a trade-off between constructing multiple parameter modes and allocating tasks per mode. Mode-Optimized Task Allocation (MOTA), our contributed adaptation strategy, trains multiple modes in parallel, then optimizes task allocation per mode. We e…
Advanced Research Lab, NavInfo Europe（四维图新欧洲高级研究实验室）
Continual learning (CL) in the brain is facilitated by a complex set of mechanisms. This includes the interplay of multiple memory systems for consolidating information as posited by the complementary learning systems (CLS) theory and synaptic consolidation for protecting the acquired knowledge from erasure. Thus, we propose a general CL method that creates a synergy between SYNaptic consolidation and dual memory Experience Replay (SYNERgy). Our method maintains a semantic memory that accumulates and consolidates information across the tasks and interacts with the episodic memory for effective…
Overcoming Domain Drift in Online Continual Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Suzhou University of Science and Technology（苏州科技大学）；Youtu Lab, Tencent（腾讯优图实验室）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
FPPL: An Efficient and Non-IID Robust Federated Continual Learning Framework
School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；School of Software Engineering, TongJi University（同济大学软件工程学院）
Deakin University（迪肯大学）；Huazhong University of Science and Technology（华中科技大学）；Qilu University of Technology（齐鲁工业大学）；Shandong Computer Science Center（山东省计算机科学中心）；Swinburne University of Technology（斯威本科技大学）
Fine-tuning attacks are effective in removing the embedded watermarks in deep learning models. However, when the source data is unavailable, it is challenging to just erase the watermark without jeopardizing the model performance. In this context, we introduce Attention Distraction (AD), a novel source data-free watermark removal attack, to make the model selectively forget the embedded watermarks by customizing continual learning. In particular, AD first anchors the model's attention on the main task using some unlabeled data. Then, through continual learning, a small number of \textit{lures}…
Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）；School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications（北京邮电大学计算机学院）；School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics（西南财经大学计算学院）；School of Computer Science, University of Technology Sydney（悉尼大学计算机科学学院）；Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港理工大学计算机科学与工程学院）
Hyperbolic Multimodal Continual Learning: A Closest-Admissible Solution
The Chinese University of Hong Kong（香港中文大学）；National University of Singapore（新加坡国立大学）；Yale University（耶鲁大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The 63rd Research Institute, National University of Defense Technology, Nanjing（国防科技大学第六十三研究所，南京）
Accurate Forgetting for Heterogeneous Federated Continual Learning
Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能研究院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；The University of Auckland（奥克兰大学）；RIKEN（理化学研究所）；Hong Kong Baptist University（香港浸会大学）；DataCanvas Technology Co., Ltd.（数帆科技有限公司）；The University of Tokyo（东京大学）
