CoMemNet is a dual-branch continual learning model for dynamic traffic networks that combines contrastive sampling via Wasserstein features and memory replay to achieve SOTA performance while mitigating forgetting.
A comprehensive survey of continual learning: Theory, method and application,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ELC uses evidential uncertainty to enable selective prediction in lifelong radar pulse classification, improving recall by up to 46% at low SNR compared to a Bayesian alternative.
citing papers explorer
-
CoMemNet: Contrastive Sampling with Memory Replay Network for Continual Traffic Prediction
CoMemNet is a dual-branch continual learning model for dynamic traffic networks that combines contrastive sampling via Wasserstein features and memory replay to achieve SOTA performance while mitigating forgetting.
-
ELC: Evidential Lifelong Classifier for Uncertainty Aware Radar Pulse Classification
ELC uses evidential uncertainty to enable selective prediction in lifelong radar pulse classification, improving recall by up to 46% at low SNR compared to a Bayesian alternative.