Imagen de Portada

Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, JinLi, Bai, Liang, Yang, Xian
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Understanding the Role of Rehearsal Scale in Continual Learning under Varying Model Capacities
por: He, JinLi, et al.
Publicado: (2026)

Understanding Generalization and Forgetting in In-Context Continual Learning
por: Li, Guangyu, et al.
Publicado: (2026)

Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis
por: Yang, Mutian, et al.
Publicado: (2026)

Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
por: Tiwari, Anushka, et al.
Publicado: (2026)

C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models
por: Zhang, Xin, et al.
Publicado: (2025)

Can We Theoretically Quantify the Impacts of Local Updates on the Generalization Performance of Federated Learning?
por: Ju, Peizhong, et al.
Publicado: (2024)

Timely Parameter Updating in Over-the-Air Federated Learning
por: Zhu, Jiaqi, et al.
Publicado: (2025)

Forget Forgetting: Continual Learning in a World of Abundant Memory
por: Cho, Dongkyu, et al.
Publicado: (2025)

Understanding Forgetting in Continual Learning with Linear Regression
por: Ding, Meng, et al.
Publicado: (2024)

Spurious Forgetting in Continual Learning of Language Models
por: Zheng, Junhao, et al.
Publicado: (2025)

No Forgetting Learning: Buffer-free Continual Learning Classification
por: Vahedifar, Mohammad Ali, et al.
Publicado: (2025)

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
por: Zhu, Yunqin, et al.
Publicado: (2026)

Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
por: Dai, Hao, et al.
Publicado: (2025)

On the Implicit Adversariality of Catastrophic Forgetting in Deep Continual Learning
por: Peng, Ze, et al.
Publicado: (2025)

Data-dependent and Oracle Bounds on Forgetting in Continual Learning
por: Friedman, Lior, et al.
Publicado: (2024)

CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay
por: Zhang, Jianshu, et al.
Publicado: (2024)

Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
por: Wang, Xinrui, et al.
Publicado: (2024)

ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
por: Guo, Zirun, et al.
Publicado: (2025)

Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
por: You, Haochen, et al.
Publicado: (2025)

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
por: Chen, Liang, et al.
Publicado: (2025)

Sequencing to Mitigate Catastrophic Forgetting in Continual Learning
por: Moussa, Hesham G., et al.
Publicado: (2025)

Accurate Forgetting for Heterogeneous Federated Continual Learning
por: Wuerkaixi, Abudukelimu, et al.
Publicado: (2025)

Bipartite Graph Attention-based Clustering for Large-scale scRNA-seq Data
por: Liang, Zhuomin, et al.
Publicado: (2026)

Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis
por: He, Yiling, et al.
Publicado: (2025)

Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks
por: Jin, Dian, et al.
Publicado: (2025)

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
por: Wang, Zhenyi, et al.
Publicado: (2023)

Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
por: Liang, Jinglin, et al.
Publicado: (2024)

GaLLoP: Gradient-based Sparse Learning on Low-Magnitude Parameters
por: Choudhary, Anand, et al.
Publicado: (2025)

Is Parameter Isolation Better for Prompt-Based Continual Learning?
por: Li, Jiangyang, et al.
Publicado: (2026)

Forget to Generalize: Iterative Adaptation for Generalization in Federated Learning
por: Alotaibi, Abdulrahman, et al.
Publicado: (2026)

Learning to Forget: Continual Learning with Adaptive Weight Decay
por: Ramesh, Aditya A., et al.
Publicado: (2026)

Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning
por: Poole, Benjamin, et al.
Publicado: (2026)

Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods
por: Fernandez, Andres, et al.
Publicado: (2025)

Mitigating Forgetting in Continual Learning with Selective Gradient Projection
por: Singh, Anika, et al.
Publicado: (2026)

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
por: Elsayed, Mohamed, et al.
Publicado: (2024)

GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay
por: Zhang, Yunan, et al.
Publicado: (2025)

Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability
por: Masip, Sergi, et al.
Publicado: (2026)

Sparse Orthogonal Parameters Tuning for Continual Learning
por: Ning, Kun-Peng, et al.
Publicado: (2024)

Continual Learning of Achieving Forgetting-free and Positive Knowledge Transfer
por: Wang, Zhi, et al.
Publicado: (2026)

Merge before Forget: A Single LoRA Continual Learning via Continual Merging
por: Qiao, Fuli, et al.
Publicado: (2025)