Cover Image

Revisiting Softmax Masking: Stop Gradient for Enhancing Stability in Replay-based Continual Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Hoyong, Kwon, Minchan, Kim, Kangil
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Asymptotic Midpoint Mixup for Margin Balancing and Moderate Broadening
by: Kim, Hoyong, et al.
Published: (2024)

Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs
by: Jung, Hee-Jun, et al.
Published: (2025)

CFASL: Composite Factor-Aligned Symmetry Learning for Disentanglement in Variational AutoEncoder
by: Jung, Hee-Jun, et al.
Published: (2024)

Teaching AI to Remember: Insights from Brain-Inspired Replay in Continual Learning
by: Kim, Jina
Published: (2025)

Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
by: Abbes, Istabrak, et al.
Published: (2025)

Efficient Parallel Audio Generation using Group Masked Language Modeling
by: Jeong, Myeonghun, et al.
Published: (2024)

Learning from Matured Dumb Teacher for Fine Generalization
by: Jung, HeeSeung, et al.
Published: (2021)

Adaptive Sparsified Graph Learning Framework for Vessel Behavior Anomalies
by: Kim, Jeehong, et al.
Published: (2025)

Logit Dynamics in Softmax Policy Gradient Methods
by: Li, Yingru
Published: (2025)

FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
by: Lee, Gihun, et al.
Published: (2023)

Spatio-Temporal Graphs Beyond Grids: Benchmark for Maritime Anomaly Detection
by: Kim, Jeehong, et al.
Published: (2025)

Better Generative Replay for Continual Federated Learning
by: Qi, Daiqing, et al.
Published: (2023)

Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring
by: Jung, Hee-Jun, et al.
Published: (2022)

Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay
by: Liu, Jinmei, et al.
Published: (2024)

Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning
by: Wu, Xinlan, et al.
Published: (2025)

DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning
by: Choi, Seungyoon, et al.
Published: (2024)

Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
by: Ding, Meng, et al.
Published: (2026)

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

Communication-Efficient Federated Learning with Accelerated Client Gradient
by: Kim, Geeho, et al.
Published: (2022)

Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems
by: Minhas, Mishal Fatima, et al.
Published: (2025)

FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning
by: Kim, Seongyoon, et al.
Published: (2024)

Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization
by: Rezazadeh, Navid, et al.
Published: (2026)

Implicit Regularization of Gradient Flow on One-Layer Softmax Attention
by: Sheen, Heejune, et al.
Published: (2024)

Heuristic Algorithm-based Action Masking Reinforcement Learning (HAAM-RL) with Ensemble Inference Method
by: Choi, Kyuwon, et al.
Published: (2024)

AL-GNN: Privacy-Preserving and Replay-Free Continual Graph Learning via Analytic Learning
by: Zhang, Xuling, et al.
Published: (2025)

Efficient Diversity-based Experience Replay for Deep Reinforcement Learning
by: Zhao, Kaiyan, et al.
Published: (2024)

Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic
by: Lee, Jeong Woon, et al.
Published: (2026)

Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
by: Liu, Jinyi, et al.
Published: (2023)

Scalable Strategies for Continual Learning with Replay
by: Hickok, Truman
Published: (2025)

Beyond 5G Network Failure Classification for Network Digital Twin Using Graph Neural Network
by: Isah, Abubakar, et al.
Published: (2024)

CUER: Corrected Uniform Experience Replay for Off-Policy Continuous Deep Reinforcement Learning Algorithms
by: Yenicesu, Arda Sarp, et al.
Published: (2024)

Universal Approximation with Softmax Attention
by: Hu, Jerry Yao-Chieh, et al.
Published: (2025)

Revisiting Random Walks for Learning on Graphs
by: Kim, Jinwoo, et al.
Published: (2024)

Learning Flexible Forward Trajectories for Masked Molecular Diffusion
by: Seo, Hyunjin, et al.
Published: (2025)

To Softmax, or not to Softmax: that is the question when applying Active Learning for Transformer Models
by: Gonsior, Julius, et al.
Published: (2022)

Experience Replay Addresses Loss of Plasticity in Continual Learning
by: Wang, Jiuqi, et al.
Published: (2025)

Minimalist Softmax Attention Provably Learns Constrained Boolean Functions
by: Hu, Jerry Yao-Chieh, et al.
Published: (2025)

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
by: Qiu, Haomiao, et al.
Published: (2025)

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
by: Miao, Yuchun, et al.
Published: (2026)

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
by: Cloud, Alex, et al.
Published: (2024)