# Learnable Parameter Similarity

## TL;DR

This paper introduces LPS, a method that learns to measure the semantic similarity between trained models' parameters, revealing relationships between visual tasks and aiding transfer learning.

## Contribution

It proposes a novel second-order neural network approach for parameter similarity measurement and creates ModelSet500 as a benchmark for this task.

## Key findings

- LPS effectively measures parameter similarity across models.
- ModelSet500 provides a comprehensive benchmark for similarity learning.
- Experiments validate the method's ability to uncover task relations.

## Abstract

Most of the existing approaches focus on specific visual tasks while ignoring the relations between them. Estimating task relation sheds light on the learning of high-order semantic concepts, e.g., transfer learning. How to reveal the underlying relations between different visual tasks remains largely unexplored. In this paper, we propose a novel \textbf{L}earnable \textbf{P}arameter \textbf{S}imilarity (\textbf{LPS}) method that learns an effective metric to measure the similarity of second-order semantics hidden in trained models. LPS is achieved by using a second-order neural network to align high-dimensional model parameters and learning second-order similarity in an end-to-end way. In addition, we create a model set called ModelSet500 as a parameter similarity learning benchmark that contains 500 trained models. Extensive experiments on ModelSet500 validate the effectiveness of the proposed method. Code will be released at \url{https://github.com/Wanggcong/learnable-parameter-similarity}.