PrimeKG-CL supplies the first continual graph learning benchmark using authentic temporal snapshots from nine biomedical databases, showing strong interactions between embedding decoders and learning strategies plus limits of standard metrics on retention versus forgetting.
Overcoming catastrophic forgetting in neural networks.Proceedings of the National Academy of Sciences, 114(13):3521–3526
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
baseline 2
background 1
method 1
citation-polarity summary
representative citing papers
RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
Expert upcycling duplicates experts in an existing MoE checkpoint and continues pre-training to match fixed-size baseline performance with 32% less compute.
CMKL delivers a 60% gain in average precision on continual entity classification in a 129K-entity biomedical KG benchmark by fusing multimodal features and protecting against modality-specific forgetting, while relationship prediction stays comparable to baselines.
BRPC is an online Bayesian calibration framework that decouples parameter tracking from discrepancy modeling for gradual nonstationarity and adds restart mechanisms to handle abrupt regime shifts.
C-Nav is a continual visual navigation framework with dual-path anti-forgetting via feature distillation and replay plus adaptive sampling that outperforms baselines on a new continual object navigation benchmark while using less memory.
SCM enables LLMs to achieve perfect recall in ten-turn conversations by using sleep-like consolidation and adaptive forgetting to reduce memory noise by over 90%.
citing papers explorer
No citing papers match the current filters.