SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.14633 · NeurIPS · 2021

Similarity and Matching of Neural Network Representations

Adrián Csiszárik, Dániel Varga, Péter Kőrösi-Szabó, Ákos Matszangosz, Gergely Papp

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
renyi-ai/drfrankenstein canonical 1 of 1
FunctionStatusWhere it lives
get_hits_overlap Ran renyi-ai/drfrankenstein/stitch_nets.py
code served (permissive licence) · get_code("61a1d8f86cc821f9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We employ a toolset -dubbed Dr. Frankenstein -to analyse the similarity of representations in deep neural networks. With this toolset, we aim to match the activations on given layers of two trained neural networks by joining them with a stitching layer. We demonstrate that the inner representations emerging in deep convolutional neural networks with the same architecture but different initializations can be matched with a surprisingly high degree of accuracy even with a single, affine stitching layer. We choose the stitching layer from several possible classes of linear transformations and investigate their performance and properties. The task of matching representations is closely related to notions of similarity. Using this toolset, we also provide a novel viewpoint on the current line of research regarding similarity indices of neural network representations: the perspective of the performance on a task. 35th Conference on Neural Information Processing Systems (NeurIPS 2021).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2110.14633")
get_code_for_paper("2110.14633")
have("2110.14633")

Connect an agent — have() is free.