Efficient and Joint Hyperparameter and Architecture Search for Collaborative Filtering

TL;DR

This paper introduces a joint hyperparameter and architecture search method for collaborative filtering models, reducing search space and evaluation costs, leading to improved performance over existing models.

Contribution

It proposes a two-stage search algorithm that considers hyperparameters and architecture jointly, with a novel reduction of the search space based on hyperparameter usefulness.

Findings

Achieves better performance than hand-designed and previous searched models.

Reduces evaluation costs using subsampled datasets in the first stage.

Demonstrates effectiveness through extensive experiments and case studies.

Abstract

Automated Machine Learning (AutoML) techniques have recently been introduced to design Collaborative Filtering (CF) models in a data-specific manner. However, existing works either search architectures or hyperparameters while ignoring the fact they are intrinsically related and should be considered together. This motivates us to consider a joint hyperparameter and architecture search method to design CF models. However, this is not easy because of the large search space and high evaluation cost. To solve these challenges, we reduce the space by screening out usefulness yperparameter choices through a comprehensive understanding of individual hyperparameters. Next, we propose a two-stage search algorithm to find proper configurations from the reduced space. In the first stage, we leverage knowledge from subsampled datasets to reduce evaluation costs; in the second stage, we efficiently fine-tune top candidate models on the whole dataset. Extensive experiments on real-world datasets show better performance can be achieved compared with both hand-designed and previous searched models. Besides, ablation and case studies demonstrate the effectiveness of our search framework.