Uniform Herding: Exemplar Replay with Representation Refresh

2026-08-13 · Krishna Subedi arxiv

As the feature representation changes, replay must preserve the earlier classes. However, only a bounded active exemplar set can be replayed. We propose Uniform Herding, which allocates the current active set across observed classes and uses a bounded candidate pool to refresh their chosen exemplars in the current representation. On CIFAR-100 with ten class-incremental tasks, a ResNet-18 backbone, active budget $M=2{,}000$, retrieval budget $b=64$, and three seeds, Uniform Herding obtains $44.00\pm0.51\%$ final average accuracy and $17.22\pm0.43\%$ forgetting, compared with $42.33\pm1.20\%$ and $24.87\pm1.11\%$ for iCaRL. Within the Uniform Herding protocol, final accuracy decreased when NME or herding was replaced with the tested alternatives, while forgetting increased when distillation was removed. Changing the retrieval budget has a smaller effect across the tested range than changing the active budget. The comparison with iCaRL is end-to-end. It does not isolate the effect of refresh from the other protocol differences. These results are limited to the tested protocol.

📄 PDF Abstract BibTeX arXiv:2608.13061

Code (0)

등록된 구현이 없습니다.

Integrating Curricula with Replays: Its Effects on Continual Learning

2023-07-08 · Ren Jie Tee, Mengmi Zhang

Humans engage in learning and reviewing processes with curricula when acquiring new skills or knowledge. This human learning behavior has inspired the integration of curricula with replay methods in continual learning ag…

Continual Learning Transfer Learning

Paused Agent Replay Refresh

2022-09-26 · Benjamin Parr

Reinforcement learning algorithms have become more complex since the invention of target networks. Unfortunately, target networks have not kept up with this increased complexity, instead requiring approximate solutions t…

Montezuma's Revenge reinforcement-learning Reinforcement Learning (RL)

Lucid Dreaming for Experience Replay: Refreshing Past States with the Current Policy

2020-09-29 · Yunshu Du, Garrett Warnell, Assefaw Gebremedhin, Peter Stone 외

Experience replay (ER) improves the data efficiency of off-policy reinforcement learning (RL) algorithms by allowing an agent to store and reuse its past experiences in a replay buffer. While many techniques have been pr…

Atari Games Reinforcement Learning (RL)

IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay

2021-04-21 · Jian Jiang, Edoardo Cetin, Oya Celiktutan

Incremental learning aims to enable machine learning models to continuously acquire new knowledge given new classes, while maintaining the knowledge already learned for old classes. Saving a subset of training samples of…

Contrastive Learning Incremental Learning

FuseSampleAgg: One-Pass Neighborhood Estimation for Budgeted Knowledge-Graph Refresh and Validation

2025-11-17 · Aleksandar Stanković, Haoran Du, Xinming Wang arxiv

Operational knowledge-graph (KG) pipelines in networking and cybersecurity increasingly need to refresh embeddings under strict time, memory, and audit budgets, especially as curated feeds and LLM-assisted extraction acc…