Skip to content
#graph neural networks Book Open access

SA-GSL: Simulated Annealing for Graph Structure Learning

Nov 2026 · Proceedings of the 35th ACM International Conference on Information and Knowledge Management · 0 citations · 76 references
Advanced Graph Neural Networks

Abstract

Graph Neural Networks (GNNs) have become a cornerstone for applications involving graph data. However, the performance of GNNs is critically dependent on the underlying graph structure. This presents a fundamental challenge, as a predefined topology may not be optimal for the specific learning task, limiting the model's performance. This limitation is particularly pronounced in heterophilous settings, where the inherent homophily assumption of GNNs contradicts the actual graph structure, causing models that rely on raw topology to fail. Although Graph Structure Learning (GSL) aims to address this issue, most existing methods use continuous relaxations of the graph topology to enable gradient-based optimization. This approach can trap models in local optima and fail to capture the discrete nature of graph data. To address this issue, we introduce a novel GSL algorithm, Simulated Annealing for Graph Structure Learning (SA-GSL), that leverages Simulated Annealing (SA) to optimize the discrete graph structure, effectively adapting the topology to handle heterophily. The SA algorithm operates as a gradient-free refiner proposing new topologies, guided by a multi-objective energy function that uses a lightweight Label Propagation model as a proxy while simultaneously promoting sparsity. An ensemble of candidate structures is generated at each step and combined via majority voting. The final graph is weighted between the original topology and the SA refined ensemble structure. Our experiments reveal that SA-GSL is highly effective, achieving state-of-the-art results on several key node classification benchmarks (1.5% on Cora, 3% on Minesweeper). The code implementation is publicly available on our GitHub repository (https://github.com/ashba93/sa-gsl).

Read PDF

Similar papers

#computer vision Review Open access Mar 2016

Determinants of overweight or obesity among ever-married adult women in Bangladesh

The findings of the study indicate that a large number of women in Bangladesh are suffering from being overweight or obese, and multiple factors are responsible for this including, older age,being from wealthy households, higher education, being from food-secured households, watching TV at least once a week, and being...

Haribondhu Sarma, N. Saquib, M. Hasan et al. · 75 citations · ⚡5
#artificial intelligence Open access Sep 2026

Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders

The rapid growth of scientific literature makes it increasingly challenging for researchers to identify novel and impactful ideas, especially across disciplines. Modern artificial intelligence (AI) systems offer new opportunities for scientific ideation, but how compelling are AI-generated ideas, and how can their qual...

Xuemei Gu, Mario Krenn · 65 citations
#computer vision Conference Aug 2008

Scrum in a Multiproject Environment: An Ethnographically-Inspired Case Study on the Adoption Challenges

Agile methods continue to gain popularity. In particular, the Scrum method appears to be on the verge of becoming a de-facto standard in the industry, leading the so called Agile movement. While there are success stories and recommendations, there is little scientifically valid evidence of the challenges in the adoptio...

A. Marchenko, P. Abrahamsson · 59 citations · ⚡11
#data science Review Open access Apr 2022

Association between Mother’s Education and Infant and Young Child Feeding Practices in South Asia

Findings demonstrate a strong positive association between mother’s education and IYCF indicators and suggest strengthening national policies to educate women at least to the secondary level in SACs might be a cost-effective intervention for improving IY CF practices.

M. Tariqujjaman, M. Hasan, M. Mahfuz et al. · 45 citations · ⚡4
#computer vision Open access Sep 2012

Making the leap to a software platform strategy: Issues and challenges

A comprehensive taxonomy of the challenges faced when a medium-scale organization decided to adopt software platforms is provided, namely: business challenges, organizational challenges, technical challenges, and people challenges.

Yaser Ghanam, F. Maurer, P. Abrahamsson · 41 citations · ⚡3

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.