AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Enhancing Noise Resilience in Face Clustering via Sparse Differential Transformer

Dafeng Zhang, Yongqi Song, Shizhuo Liu

AAAI 2026 · Graph learning › Graph algorithms and clustering · approach: Neural and local graph clustering · 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
replace vanilla Transformer with Differential Transformer (ablation)Face clustering predictor · MS1M 584K unlabeledPairwise F-score: 94.25 -> 95.05Improved
add Top-K attention mask to Diff Transformer (ablation)Diff Transformer · MS1M 584K unlabeledPairwise F-score: 95.05 -> 95.34Improved
add Top-K attention mask to vanilla Transformer (ablation)Vanilla Transformer · MS1M 584K unlabeledPairwise F-score: 94.25 -> 94.78Improved
add MoE over Top-(K-u), Top-K, Top-(K+u) masks (ablation)SDT · MS1M 584K unlabeledPairwise F-score: 95.34 -> 95.46Improved
replace exponential distance transform with sigmoid (delta=7.5) (ablation)FC-ESER · MS1M 584K unlabeledPairwise F-score: 94.49 -> 94.67Improved
use sigmoid steepness delta=5.0 instead of exp transform (ablation)FC-ESER · MS1M 584K unlabeledPairwise F-score: 94.49 -> 94.09Hurt
use sigmoid steepness delta=10.0 instead of 7.5 (ablation)FC-ESER · MS1M 584K unlabeledPairwise F-score: 94.67 -> 94.45Hurt
add Top-K Jaccard restricted to predicted neighbors (ablation)FC-ESER + Eq. (6) · MS1M 584K unlabeledPairwise F-score: 94.67 -> 95.02Improved
replace vanilla with Diff Transformer in LCEPCE (ablation)LCEPCE · DeepFashionPairwise F-score: 38.43 -> 41.76Improved
replace vanilla with Diff Transformer in LCEPCE (ablation)LCEPCE · MS1M 584KPairwise F-score: 93.43 -> 94.68Improved
vary score threshold eta from 0.5 to 0.9 (ablation)MoE-SDT · MS1M 584K unlabeledPairwise F-score: 95.34 -> 95.46No clear effect
vary kNN graph size K (40, 80, 160) (ablation)MoE-SDT · MS1M 584K unlabeledPairwise F-score: 95.32 / 95.46 / 95.34No clear effect

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