Unified Graph Networks (UGN): A Deep Neural Framework for Solving Graph Problems
Rudrajit Dawn, Madhusudan Ghosh, Partha Basuchowdhuri, Sudip Kumar Naskar
TL;DR
UGN presents a unified encoder–decoder framework that hybridizes graph convolutional networks with 2D convolutional decoding to address diverse graph problems within a single model. Key innovations include supernode features for scalable processing, an unsupervised loss for semi-supervised tasks, and the Mean Target Connectivity Matrix for efficient handling of complete graphs. Across twelve datasets spanning IoT, chemistry, social networks, biology, and knowledge graphs, UGN achieves state-of-the-art or near-state-of-the-art results on the majority of tasks, illustrating strong generalization and task transfer capabilities. The approach demonstrates practical impact by offering a flexible, resource-efficient graph-learning paradigm suitable for real-world applications like fraud detection, drug discovery, recommendation, and brain network analysis.
Abstract
Deep neural networks have enabled researchers to create powerful generalized frameworks, such as transformers, that can be used to solve well-studied problems in various application domains, such as text and image. However, such generalized frameworks are not available for solving graph problems. Graph structures are ubiquitous in many applications around us and many graph problems have been widely studied over years. In recent times, there has been a surge in deep neural network based approaches to solve graph problems, with growing availability of graph structured datasets across diverse domains. Nevertheless, existing methods are mostly tailored to solve a specific task and lack the capability to create a generalized model leading to solutions for different downstream tasks. In this work, we propose a novel, resource-efficient framework named \emph{U}nified \emph{G}raph \emph{N}etwork (UGN) by leveraging the feature extraction capability of graph convolutional neural networks (GCN) and 2-dimensional convolutional neural networks (Conv2D). UGN unifies various graph learning tasks, such as link prediction, node classification, community detection, graph-to-graph translation, knowledge graph completion, and more, within a cohesive framework, while exercising minimal task-specific extensions (e.g., formation of supernodes for coarsening massive networks to increase scalability, use of \textit{mean target connectivity matrix} (MTCM) representation for achieving scalability in graph translation task, etc.) to enhance the generalization capability of graph learning and analysis. We test the novel UGN framework for six uncorrelated graph problems, using twelve different datasets. Experimental results show that UGN outperforms the state-of-the-art baselines by a significant margin on ten datasets, while producing comparable results on the remaining dataset.