AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Unbalanced Soft-Matching Distance For Neural Representational Comparison With Partial Unit Correspondence

Chaitanya Kapoor, Alex H Williams, Meenakshi Khosla

ICLR 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport

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
allow partial matching (partial soft-matching) instead of full soft-matchingsoft-matching distance · NSD voxel alignment precision (V1d + V2v)precision: 0.881 -> 0.971Improved
use partial soft-matching instead of soft-matchingsoft-matching distance · NSD voxel alignment precision, 15 region pairsprecision: V1v + V1d 0.839 -> 0.905; V2d + V3v 0.833 -> 0.971Improved
partial soft-matching versus noise-ceiling thresholding eps=0.3 on V1v + V2vParSM · NSD voxel alignment precision (V1v + V2v)precision: 0.695 (eps=0.3) vs 0.680Hurt
rank units with partial soft-matching versus correlation-based orderingalignment-based unit removal · ResNet-18 and NSDalignment scoreImproved
single partial soft-matching optimization instead of brute-force greedy removalunit ranking · ResNet-18 and NSDalignment scoreNo clear effect
use partial soft-matching with L-curve in the presence of spurious neuronssoft-matching · Synthetic signal+noise neuronstransport cost / correct matchesImproved
apply random rotation to one network's representationResNet-18 matched subpopulations · ImageNet ResNet-18 alignmentalignmentHurt
use squared Euclidean cost instead of cosine (ablation)partial soft-matching · synthetic, ResNet-18, NSDalignmentNo clear effect

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