AI Paper Atlas

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

Set Representation Auxiliary Learning with Adversarial Encoding Perturbation and Optimization

Yankai Chen, Xinni Zhang, Henry Peng Zou, Bowei He, Yangning Li, Philip S. Yu, Irwin King, Xue Liu

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias

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 Wasserstein-based SFE encoder instead of mean-pooling (ablation)SRAL · FriendsterRecall@20: 67.02 -> 91.57Improved
add linear interpolation instead of two-layer MLP for dimension completion (ablation)SRAL · FriendsterRecall@20: 75.45 -> 91.57Improved
add adversarial encoding perturbation optimization (AEPO) (ablation)SRAL · FriendsterRecall@20: 77.13 -> 91.57Improved
add adversarial learning (ablation)SRAL · FriendsterRecall@20: 87.38 -> 91.57Improved
add adversarial learning (ablation)SRAL · Bundle recommendation YoushuRecall@20: 26.94 -> 26.92No clear effect
add AEPO (ablation)SRAL · LDA-3kAUC: 66.21 -> 87.93Improved
add AEPO (ablation)SRAL · ModelNet40 (MLP)accuracy: 86.56 -> 86.53No clear effect
increase Monte Carlo trials R from 4 to 32 (ablation)SRAL · FriendsterRecall@20: 41.23 -> 91.57Improved
use Sinkhorn/KL/JS distance instead of Wasserstein (ablation)SRAL · FriendsterRecall@20Hurt
perturb intermediate encoding instead of final embeddings (DIJ) (ablation)SRAL · FriendsterRecall@20Improved
swap SSL loss for triplet, SNN or Barlow Twins (ablation)SRAL · FriendsterRecall@20No clear effect
add SRAL+ to CrossCBRCrossCBR · YoushuRecall@20: 26.41 -> 26.92Improved

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