pith. sign in

arxiv: 1905.00414 · v4 · pith:OIAU63CAnew · submitted 2019-05-01 · 💻 cs.LG · q-bio.NC· stat.ML

Similarity of Neural Network Representations Revisited

classification 💻 cs.LG q-bio.NCstat.ML
keywords representationssimilarityneuralcomparingdifferentindexnetworknetworks
0
0 comments X
read the original abstract

Recent work has sought to understand the behavior of neural networks by comparing representations between layers and between different trained models. We examine methods for comparing neural network representations based on canonical correlation analysis (CCA). We show that CCA belongs to a family of statistics for measuring multivariate similarity, but that neither CCA nor any other statistic that is invariant to invertible linear transformation can measure meaningful similarities between representations of higher dimension than the number of data points. We introduce a similarity index that measures the relationship between representational similarity matrices and does not suffer from this limitation. This similarity index is equivalent to centered kernel alignment (CKA) and is also closely connected to CCA. Unlike CCA, CKA can reliably identify correspondences between representations in networks trained from different initializations.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The physics of AI weather models

    physics.ao-ph 2026-05 unverdicted novelty 7.0

    AI weather models may simulate the atmosphere via particle positions in latent space whose updates follow gradient flow on a learned free energy functional rather than conventional physical equations.

  2. Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space

    cs.LG 2026-05 unverdicted novelty 7.0

    In a combinatorial toy setting, winning lottery tickets preserve families of compatible feature locations in early feature space that balance proximity to final codes with low interference, rather than specific weight...

  3. When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability

    cs.LG 2026-05 unverdicted novelty 7.0

    Tensor similarity is a symmetry-invariant metric that measures functional equivalence between tensor-based networks using a recursive algorithm for cross-layer mechanisms.

  4. From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models

    cs.LG 2026-05 unverdicted novelty 7.0

    Chirality emerges in SMILES translation models through an abrupt encoder-centered reorganization of representations after a long plateau, identified via checkpoint analysis and ablation.

  5. The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

    cs.LG 2026-03 unverdicted novelty 7.0

    The grokking delay in encoder-decoder models on one-step Collatz prediction stems from decoder inability to use early-learned encoder representations of parity and residue structure, with numeral base acting as a stro...

  6. In-context Learning and Induction Heads

    cs.LG 2022-09 unverdicted novelty 7.0

    Induction heads, which implement pattern completion in attention, develop at the same training stage as a sudden rise in in-context learning, providing evidence they are the primary mechanism for in-context learning i...

  7. Decoding Alignment without Encoding Alignment: A critique of similarity analysis in neuroscience

    q-bio.NC 2026-05 unverdicted novelty 6.0

    Decoding alignment metrics can remain high and unchanged even when encoding manifold topology is causally altered, so they do not imply similar function or computation across neural populations.

  8. MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining

    cs.CL 2026-04 unverdicted novelty 6.0

    MIPIC trains nested Matryoshka representations via self-distilled intra-relational alignment with top-k CKA and progressive information chaining across depths, yielding competitive performance especially at extreme lo...

  9. Pretrained Event Classification Model for High Energy Physics Analysis

    hep-ph 2024-12 unverdicted novelty 6.0

    A GNN pretrained on 120M simulated HEP events generalizes to unseen processes and ATLAS data; fine-tuning boosts accuracy especially with small datasets, with CKA showing preserved encoders but altered intermediate layers.

  10. Multi-Narrow Transformation as a Single-Model Ensemble: Boundary Conditions, Mechanisms, and Failure Modes

    cs.LG 2026-05 unverdicted novelty 5.0

    Multi-narrow single-model ensembles outperform wide baselines in low-data image classification by learning diverse features but underperform in data-rich settings where training favors few paths.

  11. Biological Plausibility and Representational Alignment of Feedback Alignment in Convolutional Networks

    cs.AI 2026-05 unverdicted novelty 5.0

    Modified feedback alignment in convolutional networks produces representations geometrically aligned with backpropagation on CIFAR-10.

  12. ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data

    cs.LG 2026-04 unverdicted novelty 5.0

    ATLAS shows constitutions induce recoverable latent geometry in LLMs that redistributes but remains detectable across models and neural perturbation data via source-defined families and AUC separations.

  13. Exploring the limits of pre-trained embeddings in machine-guided protein design: a case study on predicting AAV vector viability

    q-bio.QM 2026-02 unverdicted novelty 5.0

    Fine-tuning pre-trained embeddings is necessary for best performance in predicting AAV vector viability, with sequence-level representations excelling post-fine-tuning in datasets with sparse localized mutations.

  14. A quantitative analysis of semantic information in deep representations of text and images

    cs.CL 2025-05 unverdicted novelty 5.0

    Semantic information in deep representations is distributed across many tokens and concentrated in specific layers, with directed predictability strongest in middle layers for text and varying by modality and language.

  15. How Data Augmentation Shapes Neural Representations

    cs.LG 2026-05 unverdicted novelty 4.0

    Data augmentation produces well-behaved trajectories in shape-invariant representation space, with augmentation type steering distinct directions and geometry predicting ensembling gains.