AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Noether Embedding: Efficient Learning of Temporal Regularities

Chi Gao, Zidong Zhou, Luping Shi

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 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 loss constants Cp=1, Cn=0 (ablation)NE · ICEWS14TR detection F1: 0.78 -> 0.82Improved
reduce Cp from 1 to 0.6 at Cn=0.4 (ablation)NE · ICEWS14TR detection F1: 0.78 -> 0.29Hurt
set omega_max to 1 instead of 50 (ablation)NE · GDELTTR detection F1: 0.56 -> 0.22Hurt
increase omega_max from 10 to 800 for query (ablation)NE · GDELTTR query r: 0.92 -> 0.85Hurt
use exponential instead of linear frequency distribution (ablation)NE · GDELTTR query r: 0.24 -> 0.85Improved
use exponential instead of linear frequency distribution (ablation)NE · ICEWS14TR query r: 0.81 -> 0.82Improved
use exponential instead of linear frequency distribution (ablation)NE · ICEWS18TR query r: 0.75 -> 0.82Improved
normalize event type vectors (ablation)NE · ICEWS14TR detection F1: 0.80 -> 0.82Improved
increase embedding dimension d from 50 to 400 (ablation)NE · ICEWS14TR detection F1: 0.29 -> 0.82Improved
increase embedding dimension d from 400 to 800 (ablation)NE · ICEWS14TR detection F1: 0.82 -> 0.83No clear effect
decode with direct g(τ) instead of indirect g'(τ)NE · ICEWS14TR detection F1: 0.78 -> 0.82Improved
use NE instead of TeRoNE · ICEWS18TR detection F1: 0.64 -> 0.83Improved

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