Self-Adaptive Graph Mixture of Models

• URL: http://arxiv.org/abs/2511.13062v1
• Date: Mon, 17 Nov 2025 07:11:06 GMT
• Title: Self-Adaptive Graph Mixture of Models
• Authors: Mohit Meena, Yash Punjabi, Abhishek A, Vishal Sharma, Mahesh Chandran,
• Abstract summary: Self-Adaptive Graph Mixture of Models (SAGMM) is a modular and practical framework that learns to automatically select and combine the most appropriate GNN models.<n>We evaluate SAGMM on 16 benchmark datasets covering node classification, graph classification, regression, and link prediction tasks.
• Score: 4.3009319001455975
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Graph Neural Networks (GNNs) have emerged as powerful tools for learning over graph-structured data, yet recent studies have shown that their performance gains are beginning to plateau. In many cases, well-established models such as GCN and GAT, when appropriately tuned, can match or even exceed the performance of more complex, state-of-the-art architectures. This trend highlights a key limitation in the current landscape: the difficulty of selecting the most suitable model for a given graph task or dataset. To address this, we propose Self-Adaptive Graph Mixture of Models (SAGMM), a modular and practical framework that learns to automatically select and combine the most appropriate GNN models from a diverse pool of architectures. Unlike prior mixture-of-experts approaches that rely on variations of a single base model, SAGMM leverages architectural diversity and a topology-aware attention gating mechanism to adaptively assign experts to each node based on the structure of the input graph. To improve efficiency, SAGMM includes a pruning mechanism that reduces the number of active experts during training and inference without compromising performance. We also explore a training-efficient variant in which expert models are pretrained and frozen, and only the gating and task-specific layers are trained. We evaluate SAGMM on 16 benchmark datasets covering node classification, graph classification, regression, and link prediction tasks, and demonstrate that it consistently outperforms or matches leading GNN baselines and prior mixture-based methods, offering a robust and adaptive solution for real-world graph learning.

Related papers

• OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models [57.94189874119267]
  Multi-Agent Systems (MAS) offer a powerful paradigm for solving complex problems.<n>Current graph learning-based design methodologies often adhere to a "one-for-one" paradigm.<n>We propose OFA-TAD, a one-for-all framework that generates adaptive collaboration graphs for any task described in natural language.
  arXiv  Detail & Related papers  (2026-01-19T12:23:44Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• Beyond Model Base Selection: Weaving Knowledge to Master Fine-grained Neural Network Design [20.31388126105889]
  We propose M-DESIGN, a curated model knowledge base (MKB) pipeline for mastering neural network refinement.<n>First, we propose a knowledge weaving engine that reframes model refinement as an adaptive query problem over task metadata.<n>Given a user's task query, M-DESIGN quickly matches and iteratively refines candidate models by leveraging a graph-relational knowledge schema.
  arXiv  Detail & Related papers  (2025-07-21T07:49:19Z)
• Graph Data Selection for Domain Adaptation: A Model-Free Approach [54.27731120381295]
  Graph domain adaptation (GDA) is a fundamental task in graph machine learning.<n>We propose a novel model-free framework, GRADATE, that selects the best training data from the source domain for the classification task on the target domain.<n>We show GRADATE outperforms existing selection methods and enhances off-the-shelf GDA methods with much fewer training data.
  arXiv  Detail & Related papers  (2025-05-22T21:18:39Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)<n>This framework provides a standardized setting to evaluate GNNs across diverse datasets.<n>We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs [59.7297608804716]
  Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns.<n>Existing GNNs require careful domain-specific architecture designs and training from scratch on each dataset.<n>We propose a novel cross-domain pretraining framework, "one model for one graph"
  arXiv  Detail & Related papers  (2024-11-30T01:49:45Z)
• GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks [72.01829954658889]
  This paper introduces the mathematical definition of this novel problem setting. We devise a general framework that coordinates a single graph-shared structure learner and multiple graph-specific GNNs. The well-trained structure learner can directly produce adaptive structures for unseen target graphs without any fine-tuning.
  arXiv  Detail & Related papers  (2023-06-20T03:33:22Z)
• Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction [11.927046591097623]
  Link prediction is a relatively under-studied graph learning task, with current state-of-the-art models based on one- or two-layers of shallow graph auto-encoder (GAE) architectures. In this paper, we focus on addressing a limitation of current methods for link prediction, which can only use shallow GAEs and variational GAEs. Our proposed methods innovatively incorporate standard auto-encoders (AEs) into the architectures of GAEs, where standard AEs are leveraged to learn essential, low-dimensional representations via seamlessly integrating the adjacency information and node features
  arXiv  Detail & Related papers  (2021-03-21T14:43:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.