mlsanityData to 7 Oct 2026

Evaluating Representational Similarity Measures from the Lens of Functional Correspondence

arXiv 2411.14633 ↗First posted 21 Nov 2024q-bio.NC cs.AI cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Neuroscience and artificial intelligence (AI) both face the challenge of interpreting high-dimensional neural data, where the comparative analysis of such data is crucial for revealing shared mechanisms and differences between these complex systems. Despite the widespread use of representational comparisons and the abundance classes of comparison methods, a critical question remains: which metrics are most suitable for these comparisons? While some studies evaluate metrics based on their ability to differentiate models of different origins or constructions (e.g., various architectures), another approach is to assess how well they distinguish models that exhibit distinct behaviors. To investigate this, we examine the degree of alignment between various representational similarity measures and behavioral outcomes, employing group statistics and a comprehensive suite of behavioral metrics for comparison. In our evaluation of eight commonly used representational similarity metrics in the visual domain -- spanning alignment-based, Canonical Correlation Analysis (CCA)-based, inner product kernel-based, and nearest-neighbor methods -- we found that metrics like linear Centered Kernel Alignment (CKA) and Procrustes distance, which emphasize the overall geometric structure or shape of representations, excelled in differentiating trained from untrained models and aligning with behavioral measures, whereas metrics such as linear predictivity, commonly used in neuroscience, demonstrated only moderate alignment with behavior. These insights are crucial for selecting metrics that emphasize behaviorally meaningful comparisons in NeuroAI research.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 24 of its 58 references that are in the map. First posted on arXiv 21 Nov 2024.

Builds on

24 of 58 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2013Describing Textures in the Wildcited by 2,110
  8. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  9. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  10. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  11. 2024The Platonic Representation Hypothesiscited by 362
  12. 2014Understanding image representations by measuring their equivariance and equivalencecited by 240
12 more
  1. 2015Convergent Learning: Do different neural networks learn the same representations?cited by 215
  2. 2021Revisiting Model Stitching to Compare Neural Representationscited by 203
  3. 2023Getting aligned on representational alignmentcited by 142
  4. 2023Similarity of Neural Network Models: A Survey of Functional and Representational Measurescited by 128
  5. 2021Are Convolutional Neural Networks or Transformers more like human vision?cited by 109
  6. 2021Generalized Shape Metrics on Neural Representationscited by 109
  7. 2020On Linear Identifiability of Learned Representationscited by 103
  8. 2014Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathwaycited by 93
  9. 2023Soft Matching Distance: A metric on neural representations that captures single-neuron tuningcited by 16
  10. 2024Differentiable Optimization of Similarity Scores Between Models and Brainscited by 10
  11. 2023System identification of neural systems: If we got it right, would we know?cited by 9
  12. 2023ContraSim -- Analyzing Neural Representations Based on Contrastive Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 7.

11 papers.

  1. 2026Revisiting the Platonic Representation Hypothesis: An Aristotelian Viewcited by 33
  2. 2025Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shiftscited by 5
  3. 2026Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignmentcited by 4
  4. 2025Measuring the Measures: Discriminative Capacity of Representational Similarity Metrics Across Model Familiescited by 2
  5. 2026Global Geometry Is Not Enough for Vision Representationscited by 2
  6. 2026Stimulus symmetries can confound representational similarity analysescited by 1
  7. 2025Comparing and Integrating Different Notions of Representational Correspondence in Neural Systemscited by 0
  8. 2025Revisiting the Relation Between Robustness and Universalitycited by 0
  9. 2026Continued Pretraining of FinBERT on Finnish Histopathological Reports: Train-Time Signals and Proxy Downstream Correlationscited by 0
  10. 2026From Layers to Networks: Comparing Neural Representations via Diffusion Geometrycited by 0
  11. 2026Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networkscited by 0