# Quantifying Data Similarity Using Cross Learning

arXiv: https://arxiv.org/abs/2510.10866 · HTML: https://mlsanity.com/paper/2510.10866/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Which Tasks Should Be Learned Together in Multi-task Learning?](https://mlsanity.com/paper/1905.07553/) (2019)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [Efficiently Identifying Task Groupings for Multi-Task Learning](https://mlsanity.com/paper/2109.04617/) (2021)
- [Improving Out-of-Distribution Robustness via Selective Augmentation](https://mlsanity.com/paper/2201.00299/) (2022)
- [Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning](https://mlsanity.com/paper/1806.06193/) (2018)
- [Geometric Dataset Distances via Optimal Transport](https://mlsanity.com/paper/2002.02923/) (2020)
- [Cross-validation Confidence Intervals for Test Error](https://mlsanity.com/paper/2007.12671/) (2020)
- [Robust angle-based transfer learning in high dimensions](https://mlsanity.com/paper/2210.12759/) (2022)
- [Methods for Quantifying Dataset Similarity: a Review, Taxonomy and Comparison](https://mlsanity.com/paper/2312.04078/) (2023)
- [pFedSim: Similarity-Aware Model Aggregation Towards Personalized Federated Learning](https://mlsanity.com/paper/2305.15706/) (2023)
- [Learning Fair Classifiers via Min-Max F-divergence Regularization](https://mlsanity.com/paper/2306.16552/) (2023)
- [A unified framework for dataset shift diagnostics](https://mlsanity.com/paper/2205.08340/) (2022)
- [Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds](https://mlsanity.com/paper/2405.07393/) (2024)
- [Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis](https://mlsanity.com/paper/2407.04047/) (2024)
- [Filtered Randomized Smoothing: A New Defense for Robust Modulation Classification](https://mlsanity.com/paper/2410.06339/) (2024)
- [Learning Fair Robustness via Domain Mixup](https://mlsanity.com/paper/2411.14424/) (2024)
- [The ART of Transfer Learning: An Adaptive and Robust Pipeline](https://mlsanity.com/paper/2305.00520/) (2023)

## Built on by (most cited first, 3 of 3)

- [Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition](https://mlsanity.com/paper/2608.19885/) (2026)
- [Evidence Before Expansion: Reuse, Spawn, or Defer in Lifelong Expert Pools](https://mlsanity.com/paper/2608.19888/) (2026)
- [A Shared Encoder Is Not a Shared Task: Conditional Comparison for Deep Expert Pools](https://mlsanity.com/paper/2609.27866/) (2026)

## Abstract (arXiv)

Measuring dataset similarity is fundamental in machine learning, particularly for transfer learning and domain adaptation. In the context of supervised learning, most existing approaches quantify similarity of two data sets based on their input feature distributions, neglecting label information and feature-response alignment. To address this, we propose the Cross-Learning Score (CLS), which measures dataset similarity through bidirectional generalization performance of decision rules. We establish its theoretical foundation by linking CLS to cosine similarity between decision boundaries under canonical linear models, providing a geometric interpretation. A robust ensemble-based estimator is developed that is easy to implement and bypasses high-dimensional density estimation entirely. For transfer learning applications, we introduce a "transferable zones" framework that categorizes source datasets into positive, ambiguous, and negative transfer regions. To accommodate deep learning, we extend CLS to encoder-head architectures, aligning with modern representation-based pipelines. Extensive experiments on synthetic and real-world datasets validate the effectiveness of CLS for similarity measurement and transfer assessment.