Equivariance Discovery by Learned Parameter-Sharing
This addresses the challenge of designing equivariant models for new domains where data properties are unknown, though it appears incremental as it builds on existing equivariance concepts.
The paper tackles the problem of discovering interpretable equivariances from data when prior knowledge is unavailable, by formulating the discovery as an optimization over parameter-sharing schemes and showing empirical recovery of known equivariances like permutations and shifts.
Designing equivariance as an inductive bias into deep-nets has been a prominent approach to build effective models, e.g., a convolutional neural network incorporates translation equivariance. However, incorporating these inductive biases requires knowledge about the equivariance properties of the data, which may not be available, e.g., when encountering a new domain. To address this, we study how to discover interpretable equivariances from data. Specifically, we formulate this discovery process as an optimization problem over a model's parameter-sharing schemes. We propose to use the partition distance to empirically quantify the accuracy of the recovered equivariance. Also, we theoretically analyze the method for Gaussian data and provide a bound on the mean squared gap between the studied discovery scheme and the oracle scheme. Empirically, we show that the approach recovers known equivariances, such as permutations and shifts, on sum of numbers and spatially-invariant data.