Incremental Learning

Follow this topic Ask about this topic

Incremental learning studies how a model can learn from data that arrives over time—such as new classes, changing domains, or streaming examples—without losing what it learned before. Common approaches replay stored examples, regularize or distill the model to preserve earlier behavior, or isolate and expand parts of the model with adapters, experts, or new parameters. Methods are evaluated in settings such as class-, domain-, and task-incremental learning, using benchmarks including CIFAR-100, ImageNet variants, and language-task sequences; newer work also considers pretrained multimodal models, long-tailed data, and task-free streams. The central tension is stability versus plasticity: preserving old knowledge can hinder learning new information, while memory, model growth, task-order effects, and realistic evaluation remain open challenges.

Latest papers

146 papers17 papers in the last four weeks, down 6% on the four weeks before. 0.1% of all new papers.

CoPE-CGL: Community-aware Prototype Extraction for Replay-Free Continual Graph Learning
Oct 26, 2026Bo-Young Lim, Seokhwan Kim, Kisung Lee +1Incremental Learning
Graduate School of Data Science Seoul National University of Science and Technology Seoul, South Korea · Division of Computer Science and Engineering Louisiana State University Baton Rouge, Louisiana, USA
Memory-Centric Continual Learning for AI Agents
Oct 21, 2026Dongfang Li, Zhuoen Chen, Bonian Jia +25Memory-Augmented Agents Lifelong Learning Agents
LSA-PAST: Layer-Specific Adaptation and Prototype Transport for Compositional Incremental Learning
Oct 19, 2026Kyle Stein, Andrew Arash Mahyari, Guillermo Francia +2Incremental Learning Class-Incremental Learning
University of West Florida, Pensacola, FL, USA · Florida Institute for Human and Machine Cognition, Pensacola, FL, USA · Indiana Univeristy, Bloomington, IN, USA
Learning without Overwriting: Structural Knowledge Fusion for Continual Learning
Oct 18, 2026Kanishk Bakshi, Amitansu Pattanaik, Kathiravan SrinivasanClass-Incremental Learning Incremental Learning
School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu 632014, India · Defence Geoinformatics Research Establishment, Defence Research and Development Organisation, New Delhi 110054, India
Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration
Oct 15, 2026Wenju Sun, Qingyong Li, Boyang Li +4Task-Incremental Learning Incremental Learning
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, China, 100044. · College of Computing and Data Science, Nanyang Technological University, Singapore, 639798. · Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry, Wuyi University, Fujian, China, 354300.
Functional Subnetwork Localization for Efficient Continual Learning in Large Language Models
Oct 15, 2026Shuoran Jiang, Wentao Zhu, Yang Xiang +8Continual Learning for LLMs Incremental Learning
School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China · China Academy of Engineering Physics, Mianyang, China · Peng Cheng Laboratory, Shenzhen, China +2
Continual Learning for Reliable In-Sequence Molecular Communication
Oct 14, 2026Siddhant Setia, Junichi Suzuki, Tadashi NakanoReplay-Based Continual Learning Incremental Learning
Department of Computer Science, University of Massachusetts, Boston, Boston, MA, 02125, USA · Graduate School of Informatics, Osaka Metropolitan University, Osaka, Japan
SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning
Oct 14, 2026Teif Aldaajani, Huda Hakami, Maha A. ThafarRegularization-Based Continual Learning Incremental Learning
Department of Computer Science, College of Computers and Information Technology, Taif University, Taif, 21944, Saudi Arabia .
Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networks
Oct 13, 2026Francesco Panetta, Federico Di Valerio, Michela ProiettiStorage-Efficient Continual Learning Replay-Based Continual Learning
Sapienza University of Rome, Italy · Goethe University Frankfurt, Germany
When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization
Oct 11, 2026Haomiao Qiu, Yining Tang, Hongyi Wan +3Continual Learning for LLM Agents Agent Skill Learning
Harbin Institute of Technology, Shenzhen · Great Bay University · Zhejiang University
Do Artificial Neural Networks Need Dendritic Nanotubes? Two Reasons for Shrinking Importance Estimates in Continual Learning
Oct 9, 2026Saurav K. AryalRegularization-Based Continual Learning Incremental Learning
Howard University, Institute for Human Centered Artificial Intelligence, Washington, DC, USA
CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling
Oct 6, 2026Maoqi Liu, Quan Fang, Yufei HeContinual Learning for LLMs Low-Rank Adaptation
Beijing University of Posts and Telecommunications · National University of Singapore
HiER-BLS: A Hierarchy-Guided and Error-Correcting Robust Incremental Broad Learning System
Oct 5, 2026Gongli Zhang, C. L. Philip Chen, Zhulin LiuHierarchical Representation Learning Neural Network Robustness
Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, the School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China, also with the Pazhou Lab, Guangzhou 510335, China, and also with the Engineering Research Center of the Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human, Guangzhou 510641, China
MAGIC: Topology-Aware Analytic Graph Few-Shot Class-Incremental Learning
Oct 4, 2026Junlin Chen, Yuhan Wang, Xuefei Wang +3Class-Incremental Learning Continual Learning
Beihang University, Beijing, China
One-Step Curvature Probes Miss the Fitting Operator: Retained Capacity and Terminal Null-Space Correction for Continual Learning
Oct 2, 2026Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Ibne Farabi Shihab, Md Najmus SwaqeebContinual Learning Incremental Learning
Department of Computer Science and Engineering, BRAC University, Bangladesh · Department of Computer Science, Iowa State University, USA · BRAC University, Bangladesh
Width Expansion as a Method for Class Incremental Learning
Sep 29, 2026A. L. S. Conde, Y. Elkhatib, C. M. RanieriClass-Incremental Learning Dynamic Neural Networks
Institute of Geosciences and Exact Sciences, São Paulo State University (UNESP), Av. 24-A, 1515, Rio Claro, 13506-692, SP, Brazil · School of Computing Science, University of Glasgow, Glasgow, G12 8QQ, Scotland, United Kingdom
Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection
Sep 29, 2026Yuankun Xie, Xiaoxuan Guo, Xiaopeng Wang +3Audio Deepfake Detection Prompt Learning
The Hong Kong Polytechnic University, Hong Kong SAR, China · Communication University of China, Beijing, China · Beijing Institute of Technology, Beijing, China
Normative Loss Landscape Navigation: A Trajectory-Based Approach to Mitigating Forgetting in Incremental Learning
Sep 28, 2026Isabelle Aguilar, Zayn Andre Zainal, Luis Fernando Herbozo Contreras +2Class-Incremental Learning Incremental Learning
Re:Cognize -- A Framework For Open-Set Comic Character Re-Identification
Sep 27, 2026Aaditya Baranwal, Madhav Kataria, Yogesh S Rawat +1Self-Training Open-Set Recognition
Institute of Artificial Intelligence, University of Central Florida, Orlando, FL, USA
Continual Learning via Self-Probe Gradients
Sep 26, 2026Dongkyu Cho, Rumi Chunara, Sungmin ChaContinual Learning for LLMs Catastrophic Forgetting
New York University · Meta Reality Labs
When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation
Sep 26, 2026Yixuan Liu, Yuhao Sun, Sen Song +1Continual Learning Incremental Learning
Sapient Intelligence · Tsinghua University
HCPN-GCN: Scaling Hierarchical Prototype Networks with Cone Geometry for Continual Graph Learning
Sep 25, 2026Sammuel R. Silva, Vander L. S. Freitas, Gladston Moreira +2Incremental Learning Hierarchical Representation Learning
Universidade Federal de Ouro Preto, Ouro Preto 35402-163, Brasil
A Lightweight Plastic-Memory Framework for Graph Few-Shot Class-Incremental Learning
Sep 22, 2026Zihan Mei, Zhili Qin, Tongze Zhang +3Class-Incremental Learning Few-Shot Learning
University of Electronic Science and Technology of China
Lightweight Ranking Heads: Accelerating Multi-Task Experimentation in Production Recommender Systems
Sep 21, 2026Sanjay Surendranath Girija, Aniruddh Nath, Li Wei +6Learning to Rank Multi-Task Learning
Google LLC Mountain View, CA, USA
Muon Can Outperform Dedicated Continual Learning Methods
Sep 21, 2026Sebastian George Sincari, Bogdan Alexandru Gheorghe, Antonio BarbalauContinual Learning Muon Optimizer
Faculty of Mathematics and Computer Science, University of Bucharest, Bucharest, Romania · Bitdefender, Bucharest, Romania
MECAIL: Communication-Aware Incremental Learning for Object Detection with 14.6 KB Spatiotemporal Experts
Sep 21, 2026Matthias Neuwirth-Trapp, Maarten Bieshaar, Danda Paudel +3Intelligent Transportation Systems Mixture of Experts
ETH Zurich, Zurich, Switzerland. · Bosch Research, Hildesheim, Germany. · INSAIT, Sofia University “St. Kliment Ohridski”, Sofia, Bulgaria.
Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Space
Sep 15, 2026Pisante Aida, Formentin SimoneContinual Learning Incremental Learning
Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy.
CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework
Sep 15, 2026Yunxiang Fu, Meng Lou, Zicheng Liao +1Class-Incremental Learning Continual Learning
School of Computing and Data Science, The University of Hong Kong · Hong Kong Generative AI Research and Development Center
Investigating catastrophic forgetting in sound event classification
Sep 10, 2026Riccardo Casciotti, Annamaria MesarosClass-Incremental Learning Incremental Learning
Signal Processing Research Center Tampere University Tampere, Finland
Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry
Sep 9, 2026Mo Zhou, Weihang Xu, Simon S. Du +1Shallow Neural Networks Orthogonal Representation Learning
University of Washington · Amazon, Inc.

Oct 26, 2026J/K move · Enter open · S save

CoPE-CGL: Community-aware Prototype Extraction for Replay-Free Continual Graph Learning

Bo-Young Lim, Seokhwan Kim, Kisung Lee, Hyuk-Yoon Kwon

Graduate School of Data Science Seoul National University of Science and Technology Seoul, South Korea · Division of Computer Science and Engineering Louisiana State University Baton Rouge, Louisiana, USA

Incremental Learning

Open paper AskPDF arXiv

Continual graph learning (CGL) maintains models as graphs evolve without retraining from scratch, while mitigating catastrophic forgetting. Existing methods typically target either transductive or inductive settings and often store past subgraphs or require task identifiers at inference. We propose Community-aware Prototype Extraction for Continual Graph Learning (CoPE-CGL), a replay-free framework that uses a parameter-free structural prior, precomputed by multi-hop Laplacian smoothing, to anchor learning, memory, and inference. CoPE-CGL combines topology-infused bottleneck adaptation, community-level prototypes, and dynamic routing by majority vote over node-to-prototype matches. The default protocol assumes each test graph comes from one learned task; a node-level variant handles mixed-task graphs. Each task adds at most a constant amount of storage, with no past graph data retained. At equal storage and without task identifiers, CoPE-CGL matches the strongest replay baseline even when it receives true task identifiers: average performance (AP) is 95.17% and 95.72% versus 94.28% and 95.82% on Arxiv and CoraFull, respectively, with 5.9-14.0 times faster runtime and zero forgetting. Across four transductive and three inductive benchmarks and mixed streams, CoPE-CGL exceeds the second-best of up to eleven baselines by up to 1.41, 6.32, and 9.33 AP percentage points, respectively. It runs 1.3-7.9 times faster end-to-end than the most accurate competitor on each benchmark and scales to the largest benchmark graph. On graphs mixing two tasks, its node-level variant achieves the best AP among CGL methods. The design targets homophilic graphs with community structure.