Adaptive Multi-Gradient Guidance with Conflict Resolution for Limited-Sample Regression

Recent studies report that gradient guidance extracted from a single-reference model can improve Limited-Sample regression. However, one reference model may not capture all relevant characteristics of the target function, which can restrict the capacity of the learner. To address this issue, we intr...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Lin, Jiaxiang Lin, Keju Zhang, Qin Zheng, Liqiang Lin, Qianqian Chen
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/7/619
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent studies report that gradient guidance extracted from a single-reference model can improve Limited-Sample regression. However, one reference model may not capture all relevant characteristics of the target function, which can restrict the capacity of the learner. To address this issue, we introduce the <b>M</b>ulti-<b>G</b>radient <b>G</b>uided <b>N</b>etwork (MGGN), an extension of single-gradient guidance that combines gradients from several reference models. The gradients are merged through an adaptive weighting scheme, and an orthogonal-projection step is applied to reduce potential conflicts between them. Experiments on sine regression are used to evaluate the method. The results indicate that MGGN achieves higher predictive accuracy and improved stability than existing single-gradient guidance and meta-learning baselines, benefiting from the complementary information provided by multiple reference models.
ISSN:2078-2489