A Distributed Training Architecture For Combinatorial Optimization

arXiv — cs.LG•Thursday, November 13, 2025 at 5:00:00 AM

Recent advancements in graph neural networks (GNNs) have shown promise in addressing combinatorial optimization problems, but existing methods face challenges in accuracy and scalability, particularly with complex graphs. A new distributed GNN-based training framework has been proposed to tackle these issues by partitioning large graphs into smaller subgraphs, allowing for efficient local optimization. Reinforcement learning is then utilized to ensure that interactions between nodes are effectively learned. Extensive experiments conducted on real large-scale social network datasets, such as Facebook and YouTube, validate the framework's effectiveness, demonstrating that it outperforms state-of-the-art approaches in both solution quality and computational efficiency. This development not only addresses the limitations of current methods but also enhances the potential for GNNs in large-scale applications, marking a significant step forward in the field of combinatorial optimization.

— via World Pulse Now AI Editorial System

Read Original

Was this article worth reading? Share it

Recommended Readings

DEV Community2 days ago

Future of Digital Content: The Rise of AI Face Swapping

PositiveArtificial Intelligence

The article discusses the rise of AI face swapping in digital content creation, highlighting its transformative impact on platforms like Instagram, YouTube, TikTok, and Facebook. Initially a novelty, AI face swapping has evolved into a powerful tool for marketing, filmmaking, and brand storytelling, enabling creators to produce hyper-realistic face swaps in seconds. This technology is reshaping how visual content is created and consumed, reflecting the increasing demand for high-quality media in a video-centric digital landscape.

Read full article

via DEV Community

arXiv — cs.LG2 days ago

SMART: A Surrogate Model for Predicting Application Runtime in Dragonfly Systems

PositiveArtificial Intelligence

The Dragonfly network is a prominent interconnect in high-performance computing, facing challenges such as workload interference on shared network links. Traditional methods like parallel discrete event simulation (PDES) are often too computationally expensive for large-scale applications. The SMART model, which integrates graph neural networks and large language models, provides a more efficient approach for predicting application runtime, outperforming existing statistical and machine learning methods.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Heterogeneous Attributed Graph Learning via Neighborhood-Aware Star Kernels

PositiveArtificial Intelligence

The article presents the Neighborhood-Aware Star Kernel (NASK), a new graph kernel for attributed graph learning. Attributed graphs, which feature irregular topologies and a mix of numerical and categorical attributes, are prevalent in areas like social networks and bioinformatics. NASK utilizes an exponential transformation of the Gower similarity coefficient to efficiently model these attributes and incorporates multi-scale neighborhood structural information through star substructures enhanced by Weisfeiler-Lehman iterations. The theoretical proof confirms that NASK is positive definite.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Urban Incident Prediction with Graph Neural Networks: Integrating Government Ratings and Crowdsourced Reports

NeutralArtificial Intelligence

Graph neural networks (GNNs) are increasingly utilized in urban spatiotemporal forecasting, particularly for predicting infrastructure issues like potholes and rodent problems. Government inspection ratings provide insights into the state of incidents in various neighborhoods, but these ratings are limited to a sparse selection of areas. To enhance prediction accuracy, a new multiview, multioutput GNN model integrates both government ratings and crowdsourced reports, addressing biases in reporting behavior and improving the understanding of urban incidents.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

When Genes Speak: A Semantic-Guided Framework for Spatially Resolved Transcriptomics Data Clustering

PositiveArtificial Intelligence

The article discusses SemST, a new semantic-guided deep learning framework for clustering spatial transcriptomics data. This framework utilizes Large Language Models (LLMs) to interpret gene symbols, transforming them into biologically informed embeddings. By integrating these embeddings with spatial relationships through Graph Neural Networks (GNNs), SemST aims to enhance the understanding of gene expression in tissue microenvironments, achieving state-of-the-art clustering performance.

Read full article

via arXiv — cs.LG

arXiv — cs.CV2 days ago

Explicit Multimodal Graph Modeling for Human-Object Interaction Detection

PositiveArtificial Intelligence

Recent advancements in Human-Object Interaction (HOI) detection have seen the rise of Transformer-based methods. However, these methods do not adequately model the relational structures essential for recognizing interactions. This paper introduces Multimodal Graph Network Modeling (MGNM), which utilizes Graph Neural Networks (GNNs) to better capture the relationships between human-object pairs, thereby enhancing HOI detection through a four-stage graph structure and a multi-level feature interaction mechanism.

Read full article

via arXiv — cs.CV

arXiv — cs.LG2 days ago

Multi-View Polymer Representations for the Open Polymer Prediction

PositiveArtificial Intelligence

The article discusses a novel approach to polymer property prediction using a multi-view design that incorporates various representations. The system combines four families of representations: tabular RDKit/Morgan descriptors, graph neural networks, 3D-informed representations, and pretrained SMILES language models. This ensemble method achieved a public mean absolute error (MAE) of 0.057 and a private MAE of 0.082, ranking 9th out of 2241 teams in the Open Polymer Prediction Challenge at NeurIPS 2025.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Enhancing Graph Representations with Neighborhood-Contextualized Message-Passing

PositiveArtificial Intelligence

Graph neural networks (GNNs) are essential for analyzing relational data, categorized into convolutional, attentional, and message-passing variants. The standard message-passing approach, while expressive, overlooks the rich contextual information from the broader local neighborhood, limiting its ability to learn complex relationships. This article introduces a new framework called neighborhood-contextualized message-passing (NCMP) to address this limitation, enhancing the expressivity and efficiency of GNNs.

Read full article

via arXiv — cs.LG