Continual Learning (CL) is the research field addressing learning without forgetting when the data distribution is not static. This paper studies spurious features' influence on continual learning algorithms. We show that continual learning algorithms solve tasks by selecting features that are not generalizable. Our experiments highlight that continual learning algorithms face two related problems: (1) spurious features and (2) local spurious features. The first one is due to a covariate shift between training and testing data, while the second is due to the limited access to data at each training step. We study (1) through a consistent set of continual learning experiments varying spurious correlation amount and data distribution support. We show that (2) is a major cause of performance decrease in continual learning along with catastrophic forgetting. This paper presents a different way of understanding performance decrease in continual learning by highlighting the influence of (local) spurious features in algorithms capabilities.
Open Continual Feature Selection via Granular-Ball Knowledge Transfer
School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics（西南财经大学计算机与人工智能学院）；Chongqing University of Posts and Telecommunications（重庆邮电大学）；School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）
Where is the Truth? The Risk of Getting Confounded in a Continual World
Computer Science Department, TU Darmstadt, Germany.（图宾根大学计算机科学系）；Hessian Center for AI (hessian.AI), Germany.（黑森人工智能中心）；German Research Center for AI (DFKI), Germany（德国人工智能研究中心）；TU Darmstadt, Centre for Cognitive Science, Germany.（图宾根大学认知科学中心）；University of Bremen, Department of Mathematics（不莱梅大学数学系）
Stability-Plasticity Balance via Singular-Vector Selection in LLM Continual Learning
School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（未来区块链与隐私计算北京高精尖创新中心）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning
Department of Artificial Intelligence；Vertex AI Google Kirkland, USA；Department of Mechanical Engineering Texas A\&M University College Station, USA；Department of Electrical；Computer Engineering The University of Texas at Dallas Richardson, USA；Computer Science Department The University of Texas at Dallas Richardson, USA
Information-theoretic Online Memory Selection for Continual Learning
DeepMind（深度思维）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Google Brain（谷歌大脑）；Baidu Apollo（百度阿波罗）
无任务持续学习中的一个挑战性问题是从数据流中在线选择代表性重放记忆。在这项工作中，我们从信息论的角度研究了在线记忆选择问题。为了收集最多的信息，我们提出了\textit{surprise}和\textit{learnability}标准来挑选信息点并避免离群值。我们提出了一个贝叶斯模型来计算的标准，有效地利用秩一矩阵结构。我们证明，这些标准鼓励选择信息点在线记忆选择的贪心算法。此外，通过识别\textit{the timing to update the memory}的重要性，我们介绍了随机信息理论水库采样器（InfoRS），它进行高信息的选择点之间的采样。与水库采样相比，InfoRS显示出对数据不平衡的更好的鲁棒性。最后，通过对持续学习基准的实证分析，证明了该方法的有效性。
A Natural Gas Consumption Forecasting System for Continual Learning Scenarios based on Hoeffding Trees with Change Point Detection Mechanism
Faculty of Electrical Engineering and Computer Science, VŠB–Technical University of Ostrava（俄斯特拉发技术大学电气工程与计算机科学学院）；Technical University of Denmark（丹麦技术大学）；University of Science and Technology, Wroclaw（弗罗茨瓦夫科技大学）
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）
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）
MagMax: Leveraging Model Merging for Seamless Continual Learning
IDEAS NCBR；Warsaw University of Technology（华沙工业大学）；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）；Tooploox；Gdańsk University of Technology（格但斯克工业大学）
ErrorEraser: Unlearning Data Bias for Improved Continual Learning
School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics（西南财经大学计算机与人工智能学院）；School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）
