COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models

• URL: http://arxiv.org/abs/2602.17893v1
• Date: Thu, 19 Feb 2026 23:14:32 GMT
• Title: COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models
• Authors: Jiajun Shen, Yufei Jin, Yi He, xingquan Zhu,
• Abstract summary: We propose COMBA to tackle large graph learning using state space models.<n>Two key innovations: graph context gating and cross batch aggregation.<n> Experiments on benchmark networks demonstrate significant performance gains compared to baseline approaches.
• Score: 19.591073105733567
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: State space models (SSMs) have recently emerged for modeling long-range dependency in sequence data, with much simplified computational costs than modern alternatives, such as transformers. Advancing SMMs to graph structured data, especially for large graphs, is a significant challenge because SSMs are sequence models and the shear graph volumes make it very expensive to convert graphs as sequences for effective learning. In this paper, we propose COMBA to tackle large graph learning using state space models, with two key innovations: graph context gating and cross batch aggregation. Graph context refers to different hops of neighborhood for each node, and graph context gating allows COMBA to use such context to learn best control of neighbor aggregation. For each graph context, COMBA samples nodes as batches, and train a graph neural network (GNN), with information being aggregated cross batches, allowing COMBA to scale to large graphs. Our theoretical study asserts that cross-batch aggregation guarantees lower error than training GNN without aggregation. Experiments on benchmark networks demonstrate significant performance gains compared to baseline approaches. Code and benchmark datasets will be released for public access.

Related papers

• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• Bi-View Embedding Fusion: A Hybrid Learning Approach for Knowledge Graph's Nodes Classification Addressing Problems with Limited Data [1.0308647202215706]
  Bi-View is a novel hybrid approach that increases the informative content of node features in Knowledge Graphs.<n>Our approach improves downstream task performance, especially in scenarios with poor initial features.
  arXiv  Detail & Related papers  (2025-11-17T06:45:14Z)
• 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)
• Deep Learning for School Dropout Detection: A Comparison of Tabular and Graph-Based Models for Predicting At-Risk Students [0.2029906424353094]
  Student dropout is a significant challenge in educational systems worldwide.<n>Graph Neural Networks (GNNs) offer a potential advantage by capturing complex relationships inherent in student data if structured as graphs.
  arXiv  Detail & Related papers  (2025-08-09T01:19:32Z)
• Scalable Graph Generative Modeling via Substructure Sequences [50.32639806800683]
  We introduce Generative Graph Pattern Machine (G$2$PM), a generative Transformer pre-training framework for graphs.<n>G$2$PM represents graph instances (nodes, edges, or entire graphs) as sequences of substructures.<n>It employs generative pre-training over the sequences to learn generalizable and transferable representations.
  arXiv  Detail & Related papers  (2025-05-22T02:16:34Z)
• Beyond Message Passing: Neural Graph Pattern Machine [50.78679002846741]
  We introduce the Neural Graph Pattern Machine (GPM), a novel framework that bypasses message passing by learning directly from graph substructures.<n>GPM efficiently extracts, encodes, and prioritizes task-relevant graph patterns, offering greater expressivity and improved ability to capture long-range dependencies.
  arXiv  Detail & Related papers  (2025-01-30T20:37:47Z)
• 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)
• What Can We Learn from State Space Models for Machine Learning on Graphs? [11.38076877943004]
  We propose Graph State Space Convolution (GSSC) as a principled extension of State Space Models (SSMs) to graph-structured data. By leveraging global permutation-equivariant set aggregation and factorizable graph kernels, GSSC preserves all three advantages of SSMs. Our findings highlight the potential of GSSC as a powerful and scalable model for graph machine learning.
  arXiv  Detail & Related papers  (2024-06-09T15:03:36Z)
• GraphEdit: Large Language Models for Graph Structure Learning [14.16155596597421]
  Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data.<n>Existing GSL methods heavily depend on explicit graph structural information as supervision signals.<n>We propose GraphEdit, an approach that leverages large language models (LLMs) to learn complex node relationships in graph-structured data.
  arXiv  Detail & Related papers  (2024-02-23T08:29:42Z)
• Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling [60.0185734837814]
  Graph neural networks (GNNs) have found extensive applications in learning from graph data. To bolster the generalization capacity of GNNs, it has become customary to augment training graph structures with techniques like graph augmentations. This study introduces the concept of Mixture-of-Experts (MoE) to GNNs, with the aim of augmenting their capacity to adapt to a diverse range of training graph structures.
  arXiv  Detail & Related papers  (2023-04-06T01:09:36Z)
• Scalable Graph Neural Networks for Heterogeneous Graphs [12.44278942365518]
  Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data. Recent work has argued that GNNs primarily use the graph for feature smoothing, and have shown competitive results on benchmark tasks. In this work, we ask whether these results can be extended to heterogeneous graphs, which encode multiple types of relationship between different entities.
  arXiv  Detail & Related papers  (2020-11-19T06:03:35Z)

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.