Hyperparameter Learning for Deep Learning-Based Recommender Systems
- 16 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 16 (4) , 2699-2712
Abstract
Deep learning (DL)-based recommender system (RS), particularly for its advances in the recent five years, has been startling. It reshapes the architectures of traditional RSs by lifting their limitations in dealing with data sparsity and cold-start issues. Yet, the performance of DL-based RS, like many other DL-based intelligent systems, heavily relies on selecting hyperparameters. Unfortunately, the most common selection approach is still Grid Search that requires numerous computational resources and human efforts. Motivated by this, this paper proposes a general hyperparameter optimization framework, named DE-Opt, which can be applied to most existing DL-based RSs seamlessly. The main idea of DE-Opt is to incorporate differential evolution (DE) into the model training process of a DL-based RS at a layer-wise granularity to simultaneously auto-learn its two key hyperparameters, namely, the learning rate $\eta$ and the regularization coefficient $\lambda$ . As a result, the system performance in terms of recommendation accuracy and computational efficiency is uplifted. Experimental results on three benchmark datasets substantiate that: 1) DE-Opt is compatible with the most recent advancements of DL-based RS to automate their hyperparameter-tuning processes, and 2) DE-Opt excels among its state-of-the-art hyperparameter-optimization competitors in terms of both higher learning performance and lower runtime.Keywords
Funding Information
- National Natural Science Foundation of China (62072429, 62293501)
- key cooperation project of Chongqing Municipal Education Commission (HZ2021008, HZ2021017)
This publication has 41 references indexed in Scilit:
- Synthetic inertia control based on fuzzy adaptive differential evolutionInternational Journal of Electrical Power & Energy Systems, 2019
- On convergence analysis of particle swarm optimization algorithmJournal of Computational and Applied Mathematics, 2018
- Latent Relational Metric Learning via Memory-based Attention for Collaborative Ranking2018
- Neural Rating Regression with Abstractive Tips Generation for Recommendation | Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval2017
- Neural Collaborative Filtering2017
- AutoRec2015
- SEG-SSC: A Framework Based on Synthetic Examples Generation for Self-Labeled Semi-Supervised ClassificationIEEE Transactions on Cybernetics, 2014
- Learning recommender systems with adaptive regularization2012
- Scale factor local search in differential evolutionMemetic Computing, 2009
- Markov chain models of bare-bones particle swarm optimizers2007