ReSi: A Comprehensive Benchmark for Representational Similarity Measures
This provides a foundational tool for researchers to systematically compare neural representations, though it is incremental as it builds on existing similarity measures.
The authors tackled the problem of evaluating representational similarity measures for neural architectures by introducing the ReSi benchmark, which includes six tests, 24 measures, 14 architectures, and seven datasets across multiple domains, and demonstrated its utility through experiments.
Measuring the similarity of different representations of neural architectures is a fundamental task and an open research challenge for the machine learning community. This paper presents the first comprehensive benchmark for evaluating representational similarity measures based on well-defined groundings of similarity. The representational similarity (ReSi) benchmark consists of (i) six carefully designed tests for similarity measures, (ii) 24 similarity measures, (iii) 14 neural network architectures, and (iv) seven datasets, spanning over the graph, language, and vision domains. The benchmark opens up several important avenues of research on representational similarity that enable novel explorations and applications of neural architectures. We demonstrate the utility of the ReSi benchmark by conducting experiments on various neural network architectures, real world datasets and similarity measures. All components of the benchmark are publicly available and thereby facilitate systematic reproduction and production of research results. The benchmark is extensible, future research can build on and further expand it. We believe that the ReSi benchmark can serve as a sound platform catalyzing future research that aims to systematically evaluate existing and explore novel ways of comparing representations of neural architectures.