Saved in:
Bibliographic Details
Main Authors: Yao, Quanming, Zhang, Yongqi, Wang, Yaqing, Yin, Nan, Kwok, James, Yang, Qiang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.00478
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917870639775744
author Yao, Quanming
Zhang, Yongqi
Wang, Yaqing
Yin, Nan
Kwok, James
Yang, Qiang
author_facet Yao, Quanming
Zhang, Yongqi
Wang, Yaqing
Yin, Nan
Kwok, James
Yang, Qiang
contents The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due to bottlenecks in data, computation, and trust, the sustainability of this strategy is a serious concern. In this paper, we attempt to address this issue in a parsimonious manner (i.e., achieving greater potential with simpler models). The key is to drive models using domain-specific knowledge, such as symbols, logic, and formulas, instead of purely relying on scaleup. This approach allows us to build a framework that uses this knowledge as "building blocks" to achieve parsimony in model design, training, and interpretation. Empirical results show that our methods surpass those that typically follow the scaling law. We also demonstrate our framework in AI for science, specifically in the problem of drug-drug interaction prediction. We hope our research can foster more diverse technical roadmaps in the era of foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2407_00478
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Scaleup: Knowledge-aware Parsimony Learning from Deep Networks
Yao, Quanming
Zhang, Yongqi
Wang, Yaqing
Yin, Nan
Kwok, James
Yang, Qiang
Machine Learning
Artificial Intelligence
The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due to bottlenecks in data, computation, and trust, the sustainability of this strategy is a serious concern. In this paper, we attempt to address this issue in a parsimonious manner (i.e., achieving greater potential with simpler models). The key is to drive models using domain-specific knowledge, such as symbols, logic, and formulas, instead of purely relying on scaleup. This approach allows us to build a framework that uses this knowledge as "building blocks" to achieve parsimony in model design, training, and interpretation. Empirical results show that our methods surpass those that typically follow the scaling law. We also demonstrate our framework in AI for science, specifically in the problem of drug-drug interaction prediction. We hope our research can foster more diverse technical roadmaps in the era of foundation models.
title Beyond Scaleup: Knowledge-aware Parsimony Learning from Deep Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2407.00478