Saved in:
Bibliographic Details
Main Authors: Wang, Jialiang, Bao, Xueyan, Wu, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.16277
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909968670654464
author Wang, Jialiang
Bao, Xueyan
Wu, Hao
author_facet Wang, Jialiang
Bao, Xueyan
Wu, Hao
contents Second-order Latent Factor (SLF) model, a class of low-rank representation learning methods, has proven effective at extracting node-to-node interaction patterns from High-dimensional and Incomplete (HDI) data. However, its optimization is notoriously difficult due to its bilinear and non-convex nature. Sharpness-aware Minimization (SAM) has recently proposed to find flat local minima when minimizing non-convex objectives, thereby improving the generalization of representation-learning models. To address this challenge, we propose a Sharpness-aware SLF (SSLF) model. SSLF embodies two key ideas: (1) acquiring second-order information via Hessian-vector products; and (2) injecting a sharpness term into the curvature (Hessian) through the designed Hessian-vector products. Experiments on multiple industrial datasets demonstrate that the proposed model consistently outperforms state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16277
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sharpness-aware Second-order Latent Factor Model for High-dimensional and Incomplete Data
Wang, Jialiang
Bao, Xueyan
Wu, Hao
Machine Learning
Second-order Latent Factor (SLF) model, a class of low-rank representation learning methods, has proven effective at extracting node-to-node interaction patterns from High-dimensional and Incomplete (HDI) data. However, its optimization is notoriously difficult due to its bilinear and non-convex nature. Sharpness-aware Minimization (SAM) has recently proposed to find flat local minima when minimizing non-convex objectives, thereby improving the generalization of representation-learning models. To address this challenge, we propose a Sharpness-aware SLF (SSLF) model. SSLF embodies two key ideas: (1) acquiring second-order information via Hessian-vector products; and (2) injecting a sharpness term into the curvature (Hessian) through the designed Hessian-vector products. Experiments on multiple industrial datasets demonstrate that the proposed model consistently outperforms state-of-the-art baselines.
title Sharpness-aware Second-order Latent Factor Model for High-dimensional and Incomplete Data
topic Machine Learning
url https://arxiv.org/abs/2512.16277