Scalable and Interpretable Representation Alignment with Ordinal Similarity

• URL: http://arxiv.org/abs/2606.16379v2
• Date: Tue, 16 Jun 2026 08:16:11 GMT
• Title: Scalable and Interpretable Representation Alignment with Ordinal Similarity
• Abstract summary: We develop an ordinal-similarity framework, instantiated by the Triplet (TSI) and Quadruplet (QSI) Similarity Indices.<n>We demonstrate this formulation is inherently interpretable, robust to outliers, and computationally efficient.
• Score: 4.6220510592774575
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evaluating representation similarity is fundamental to representation learning. However, existing metrics suffer from significant limitations: they lack interpretability due to shifting baselines, lack robustness to outliers, and are computationally intractable for large datasets, forcing reliance on heuristic approximations. To address this, we develop an ordinal-similarity framework, instantiated by the Triplet (TSI) and Quadruplet (QSI) Similarity Indices, which measure alignment by quantifying the consistency of ordinal relationships. We theoretically demonstrate this formulation is inherently interpretable, robust to outliers, and computationally efficient. Finally, we establish a formal equivalence between TSI and local neighborhood alignment, measured by Mutual Nearest Neighbors. Empirically, we validate these properties and show that ordinal similarity offers a scalable approach to measuring alignment, enabling practitioners to better understand and design representations.

Related papers

• Uncertainty-DTW for Sequences and Visual Tokens [43.798398689900075]
  We introduce uncertainty-aware alignment, a probabilistic framework that models correspondences with heteroscedastic uncertainty and performs structured matching along alignment paths.<n>We generalize this framework from temporal sequences to tokenized visual representations, enabling structured matching over sets of visual tokens.<n>These findings establish uncertainty-aware alignment as a general, robust, and interpretable framework for learning from structured data.
  arXiv  Detail & Related papers  (2026-05-24T14:49:43Z)
• The Generalized Turing Test: A Foundation for Comparing Intelligence [0.8929189891250133]
  We introduce a formal framework for comparing the capabilities of arbitrary agents via indistinguishability.<n>For agents A and B, we define the Turing comparator A $geq$ B to hold if B, acting as a distinguisher, cannot reliably distinguish between interactions with A and another instance of B.<n>This yields a dataset- and task-agnostic notion of relative intelligence.
  arXiv  Detail & Related papers  (2026-05-11T17:00:18Z)
• Barycentric alignment for instance-level comparison of neural representations [2.1920579994942164]
  We introduce a barycentric alignment framework that quotients out nuisance symmetries to construct a universal embedding space across many models.<n>We identify systematic input properties that predict representational convergence versus divergence across vision and language model families.<n>We also apply the same barycentric alignment framework to purely unimodal vision and language models and find that post-hoc alignment into a shared space yields image text similarity scores.
  arXiv  Detail & Related papers  (2026-02-09T21:49:44Z)
• Bridging Functional and Representational Similarity via Usable Information [3.9189279162842854]
  We present a unified framework for quantifying the similarity between representations through the lens of textitusable information<n>First, addressing functional similarity, we establish a formal link between stitching performance and conditional mutual information.<n>Second, concerning representational similarity, we prove that reconstruction-based metrics and standard tools act as estimators of usable information under specific constraints.
  arXiv  Detail & Related papers  (2026-01-29T11:30:55Z)
• Unifying Information-Theoretic and Pair-Counting Clustering Similarity [51.660331450043806]
  Clustering similarity measures are typically organized into two principal families, pair-counting and information-theoretic.<n>Here, we develop an analytical framework that unifies these families through two complementary perspectives.
  arXiv  Detail & Related papers  (2025-11-04T21:13:32Z)
• ASSESS: A Semantic and Structural Evaluation Framework for Statement Similarity [9.337443482551356]
  We introduce ASSESS (A Semantic and Structural Evaluation Framework for Statement Similarity), which comprehensively integrates semantic and structural information to provide a continuous similarity score.<n>For rigorous validation, we present EPLA, a new benchmark of 524 expert-annotated formal statement pairs derived from miniF2F and ProofNet.<n>Experiments on EPLA demonstrate that TransTED Similarity outperforms existing methods, achieving state-of-the-art accuracy and the highest Kappa coefficient.
  arXiv  Detail & Related papers  (2025-09-26T12:02:58Z)
• The Foundations of Tokenization: Statistical and Computational Concerns [51.370165245628975]
  Tokenization is a critical step in the NLP pipeline.<n>Despite its recognized importance as a standard representation method in NLP, the theoretical underpinnings of tokenization are not yet fully understood.<n>The present paper contributes to addressing this theoretical gap by proposing a unified formal framework for representing and analyzing tokenizer models.
  arXiv  Detail & Related papers  (2024-07-16T11:12:28Z)
• Enriching Disentanglement: From Logical Definitions to Quantitative Metrics [59.12308034729482]
  Disentangling the explanatory factors in complex data is a promising approach for data-efficient representation learning. We establish relationships between logical definitions and quantitative metrics to derive theoretically grounded disentanglement metrics. We empirically demonstrate the effectiveness of the proposed metrics by isolating different aspects of disentangled representations.
  arXiv  Detail & Related papers  (2023-05-19T08:22:23Z)
• Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects [92.80955339180119]
  mainstream crowd counting methods regress density map and integrate it to obtain counting results. Inspired by this, we propose a rational and anthropoid crowd counting framework.
  arXiv  Detail & Related papers  (2022-12-02T07:00:53Z)
• Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings [70.390286614242]
  We propose a novel regularizer -- namely, DUality-induced RegulArizer (DURA) -- which effectively encourages the entities with similar semantics to have similar embeddings. Experiments demonstrate that DURA consistently and significantly improves the performance of state-of-the-art semantic matching models.
  arXiv  Detail & Related papers  (2022-03-24T09:24:39Z)
• Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlap [140.98628848491146]
  We introduce deconfounding scores, which induce better overlap without biasing the target of estimation. We show that deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data. In particular, we show that this technique could be an attractive alternative to standard regularizations.
  arXiv  Detail & Related papers  (2021-04-12T18:50:11Z)
• 3D Correspondence Grouping with Compatibility Features [51.869670613445685]
  We present a simple yet effective method for 3D correspondence grouping. The objective is to accurately classify initial correspondences obtained by matching local geometric descriptors into inliers and outliers. We propose a novel representation for 3D correspondences, dubbed compatibility feature (CF), to describe the consistencies within inliers and inconsistencies within outliers.
  arXiv  Detail & Related papers  (2020-07-21T02:39:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.