AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Invariant Representation Learning for Memory Behavior Modeling via Adaptive Environment Separation

Xiaoxuan Shen, Zhihai Hu, Fuqing Li, Shengyingjie Liu, Jianwen Sun

AAAI 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 1 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
add the InfoMax encoder stage (vs random encoder) (ablation)I-Mem · AnkiAUC: 10% drop in AUCImproved
add the mapping step (vs using high-dimensional representations directly) (ablation)I-Mem · AnkiAUC: 24% decreaseImproved
increase spurious set size from H-1 to H-3 (ablation)I-Mem · AnkiAUC: 0.7037 -> 0.7139Improved
increase spurious set size from H-1 to H-2 (ablation)I-Mem · MaiMemoAUC: 0.5726 -> 0.5969Improved
increase spurious set size from H-2 to H-5 (ablation)I-Mem · MaiMemoAUC: 0.5969 -> 0.5692Hurt
increase spurious set size from H-1 to H-5 (ablation)I-Mem · En2EsAUC: 0.6918 -> 0.6812Hurt
increase spurious set size from H-1 to H-5 (ablation)I-Mem · En2FrAUC: 0.6691 -> 0.6691No clear effect
replace ERM with I-Mem decorrelationDKT · Average of 4 real-world datasetsAUC: 0.6069 -> 0.6593Improved
replace ERM with I-Mem decorrelationDKT · Synthetic FIIF alpha=0.6AUC: 0.6843 -> 0.7755Improved
replace ERM with I-Mem on strong-spurious FIIFDKT · Synthetic FIIF alpha=0.9MAE: 0.0950 -> 0.0941No clear effect
replace ERM with I-Mem decorrelationDKT · Synthetic FIIF alpha=0.6spurious/invariant importance: reduces dependency on spurious features by 16.9%, increases attention to invariant features by 275.1%Improved
replace ERM with I-Mem on AnkiDKT · AnkiMAE: 0.4475 -> 0.3654Mixed

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