Storage-Efficient Continual Learning

Latest papers

11 papers4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

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
SARAM: Sparse Adapter Allocation with Reuse and Merging for Lifelong Robot Learning
Oct 17, 2026SeongJun Jeong, Chungwoo Lee, Gi-Cheon Kang +1Continual Robot Learning Continual Learning for VLA Models
Seoul National University · Ajou University
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
Static Gradient Attribution Underperforms a Density-Matched Random Mask on Loss-Based Forgetting Within LoRA B-Matrix
Oct 8, 2026Yu Sun, Junwei Zhou, Zuodong Xiang +5Storage-Efficient Continual Learning Continual Learning for LLMs
University of Pennsylvania · Matter Innovation Inc. · University of California, Davis +5
CE $^4$ L: Continual Ego, Exo, and Ego-Exo Learning
Sep 20, 2026Hongwei Yan, Kanglei Zhou, Yuchen Liu +3Temporal Action Segmentation Next-Action Prediction
School of Life Sciences, IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing, China · Tsinghua-Peking Center for Life Sciences · Department of Psychological and Cognitive Sciences, Tsinghua University, Beijing, China +2
Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management
Jun 29, 2026Byeong Hoon YoonStorage-Efficient Continual Learning Continual Learning
Independent Researcher
Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
May 31, 2026Anushka Tiwari, Kaiyi JiStorage-Efficient Continual Learning Parameter-Efficient Fine-Tuning
Institute for Artificial Intelligence and Data Science, University at Buffalo, Buffalo, NY, USA · Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA
Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning
May 8, 2026Xi Wang, Cheng DengStorage-Efficient Continual Learning Continual Learning
School of Electronic Engineering, Xidian University, Xi’an, Shaanxi, China.
Temporal Memory for Resource-Constrained Agents: Continual Learning via Stochastic Compress-Add-Smooth
Mar 31, 2026Michael ChertkovMemory Compression Continual Learning
Graduate Inter-Disciplinary Program in Applied Mathematics, & Department of Mathematics, University Arizona, Tucson, AZ 85721
Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models
Mar 22, 2026Elif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin VanschorenStorage-Efficient Continual Learning Class-Incremental Learning
AMOR/e Lab, Eindhoven University of Technology
Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning
Mar 9, 2026Adrian Garcia-Castañeda, Jon Irureta, Jon Imaz +1Storage-Efficient Continual Learning Class-Incremental Learning
Ikerlan Technology Research Center, Arrasate, Spain · Goi Eskola Politeknikoa, Mondragon Unibertsitatea, Arrasate, Spain · University of the Basque Country UPV/EHU, Spain

Oct 18, 2026J/K move · Enter open · S save

Learning without Overwriting: Structural Knowledge Fusion for Continual Learning

Kanishk Bakshi, Amitansu Pattanaik, Kathiravan Srinivasan

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

Class-Incremental Learning Incremental Learning Catastrophic Forgetting Storage-Efficient Continual Learning

Open paper AskPDF arXiv

Catastrophic forgetting in sequential deep learning arises from a fixed-capacity architectural constraint: parameter updates encoding new tasks perturb weight subspaces supporting prior representations. We introduce the Knowledge Fusion Network (KFN), which mitigates the stability-plasticity trade-off in class-incremental learning through novelty-gated structural expansion rather than parameter negotiation within a shared capacity budget. KFN decouples task acquisition from knowledge consolidation: each incoming task is learned in an isolated lightweight specialist network (2.8M parameters) and integrated into the global model via a Structural Fusion Module that allocates dedicated channel capacity conditioned on a quantitative novelty score. Dual structural isolation--channel-space separation with temporally phased gradient unfreezing--protects consolidated knowledge. On ten-task Split CIFAR-100, KFN achieves 11.94% minimum task accuracy and 71.16% task-10 accuracy, whereas shared-parameter baselines degrade severely: LwF to 9.07% average accuracy (0.00% min), Replay++ to 8.91% (85.08% forgetting), and Replay to 16.21% (73.44% forgetting); KFN's forgetting (57.92%) is 15.5 pp lower than Replay. Furthermore, KFN prevents logit-scale drift, maintaining near-symmetric task performance. Across CIFAR-100 and EuroSAT satellite imagery, KFN's class-incremental retention (72.7% and 42.5%) substantially exceeds the best baselines (29.6% and 0.94%). Crucially, KFN achieves parameter-efficient linear scaling, adding 25% of the base parameter count per step and requiring 25.1% of naive backbone duplication over ten tasks (28.1M vs 112.0M). With a 37.1% peak GPU memory reduction over full retraining, KFN establishes novelty-gated expansion as a practical path beyond fixed-capacity architectures.