AI Paper Atlas

Research map / Continual learning / Online and replay-based

Online Noisy Continual Relation Learning

Guozheng Li, Peng Wang, Qiqing Luo, Yanhe Liu, Wenjun Ke

AAAI 2023 · Continual learning › Online and replay-based · approach: Plug-and-play online training enhancements · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use S6 instead of the strongest reported baselineFewRel, TACRED, and NYT-H · FewRel at 20%, 40%, 60%, and 80% noise; TACRED at 20%, 40%, 60%, and 80% noise; NYT-Hoverall accuracy (FewRel and TACRED) or macro-F1 (NYT-H): FewRel: 64.6 -> 66.1; 55.3 -> 66.0; 36.9 -> 58.8; 17.8 -> 50.1. TACRED: 78.4 -> 61.2; 47.7 -> 43.9; 18.2 -> 24.3; 8.6 ->Improved
Add noisy replay-buffer samples to clean samples during semi-supervised offline finetuning (ablation)S6 · FewRel, 80% noiseoverall accuracy (%): 49.6 -> 50.1Improved
Add noisy replay-buffer samples to clean samples during semi-supervised offline finetuning (ablation)S6 · TACRED, 80% noiseoverall accuracy (%): 10.8 -> 12.2Improved
Add noisy replay-buffer samples to clean samples during semi-supervised offline finetuning (ablation)S6 · NYT-Hmacro-F1 (%): 20.4 -> 29.1Improved
Add self-supervised contrastive online learning instead of supervised contrastive learning (ablation)S6 · FewRel and TACRED across noise ratesaccuracyImproved
Replace the sample separator's loss-based selection rules with random sampling (ablation)S6 replay-buffer selection · FewRel, first-task accuracy over subsequent tasksaccuracyHurt
Add the self-supervised online learner to GDumb's greedy sampler (ablation)GDumb · FewRel and TACRED across noise ratesaccuracyImproved
Use noisy replay samples in finetuning rather than only clean replay samples (ablation)S6 · FewRel, 80% noiseoverall accuracy (%): 49.1 -> 50.1Improved
Use noisy replay samples in finetuning rather than only clean replay samples (ablation)S6 · TACRED, 80% noiseoverall accuracy (%): 10.5 -> 12.2Improved
Use noisy replay samples in finetuning rather than only clean replay samples (ablation)S6 · NYT-Hmacro-F1 (%): 18.2 -> 29.1Improved
Apply loss-based sample purification on an extremely imbalanced dataset (ablation)S6 · NYT-H clean replay bufferclean-sample proportion: 34.5Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy