Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs

• URL: http://arxiv.org/abs/2606.01660v1
• Date: Mon, 01 Jun 2026 04:14:13 GMT
• Title: Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs
• Abstract summary: FilterMoE is a mixture-of-experts PPGNN in which a small bank of learnable Chebyshev filter experts is routed jointly over nodes and channels by a 3D gating tensor.<n>Across eleven homophilic and heterophilic datasets, FilterMoE outperforms strong PPGNN baselines on nine datasets and ranks first on all three large-scale benchmarks.<n>These results establish joint node-channel filter as a robust alternative to dataset-specific hop-aggregator selection.
• Score: 10.327331833615125
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pre-propagation graph neural networks (PPGNNs) push all graph-dependent computation into a preprocessing step and train only on the resulting dense hop features, which makes them highly scalable. A puzzle in this regime is that more complex hop aggregators do not reliably outperform simpler ones: on many benchmarks, a plain MLP-based aggregator matches or beats hop-attention variants. We revisit this behavior from a graph-filter perspective. Over a precomputed diffusion basis, existing PPGNNs differ mainly in how filter coefficients are shared across nodes and feature channels, rather than simply in raw aggregator capacity. MLP-based architectures learn channel-dependent filters that are largely shared across nodes, while hop-attention-based architectures learn node-dependent mixtures that are largely shared across channels. This reveals a missing regime in standard PPGNN designs: joint node- and channel-adaptive filtering under the pre-propagation computational contract. We propose FilterMoE, a mixture-of-experts PPGNN in which a small bank of learnable Chebyshev filter experts is routed jointly over nodes and channels by a 3D gating tensor. Across eleven homophilic and heterophilic benchmarks, FilterMoE outperforms strong PPGNN baselines on nine datasets and ranks first on all three large-scale benchmarks, improving the average test score by 1.53 points. These results establish joint node-channel filter routing as a robust alternative to dataset-specific hop-aggregator selection.

Related papers

• Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarsening [15.198274855557132]
  This paper introduces Coarsening-guided Partition-wise Filtering (CPF)<n>CPF innovates by performing filtering on node partitions.<n>In-depth analysis is conducted for each phase of CPF, showing its superiority over other paradigms.
  arXiv  Detail & Related papers  (2025-05-20T07:30:45Z)
• Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach [58.8524608686851]
  Graph Neural Networks (GNNs) have proven to be highly effective for node classification tasks across diverse graph structural patterns. Traditionally, GNNs employ a uniform global filter, typically a low-pass filter for homophilic graphs and a high-pass filter for heterophilic graphs. We introduce a novel GNN framework Node-MoE that utilizes a mixture of experts to adaptively select the appropriate filters for different nodes.
  arXiv  Detail & Related papers  (2024-06-05T17:12:38Z)
• Spatio-Spectral Graph Neural Networks [50.277959544420455]
  We propose Spatio-Spectral Graph Networks (S$2$GNNs) S$2$GNNs combine spatially and spectrally parametrized graph filters. We show that S$2$GNNs vanquish over-squashing and yield strictly tighter approximation-theoretic error bounds than MPGNNs.
  arXiv  Detail & Related papers  (2024-05-29T14:28:08Z)
• Graph Neural Networks with Diverse Spectral Filtering [32.69196871253339]
  Spectral Graph Neural Networks (GNNs) have achieved tremendous success in graph machine learning. We propose a novel diverse spectral filtering (DSF) framework, which automatically learns node-specific filter weights. Our framework can consistently boost model performance by up to 4.92% in node classification tasks.
  arXiv  Detail & Related papers  (2023-12-14T15:38:12Z)
• VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization [70.8567058758375]
  VQ-GNN is a universal framework to scale up any convolution-based GNNs using Vector Quantization (VQ) without compromising the performance. Our framework avoids the "neighbor explosion" problem of GNNs using quantized representations combined with a low-rank version of the graph convolution matrix.
  arXiv  Detail & Related papers  (2021-10-27T11:48:50Z)
• Message Passing in Graph Convolution Networks via Adaptive Filter Banks [81.12823274576274]
  We present a novel graph convolution operator, termed BankGCN. It decomposes multi-channel signals on graphs into subspaces and handles particular information in each subspace with an adapted filter. It achieves excellent performance in graph classification on a collection of benchmark graph datasets.
  arXiv  Detail & Related papers  (2021-06-18T04:23:34Z)
• Graph Neural Networks with Adaptive Frequency Response Filter [55.626174910206046]
  We develop a graph neural network framework AdaGNN with a well-smooth adaptive frequency response filter. We empirically validate the effectiveness of the proposed framework on various benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-26T19:31:21Z)
• Self-grouping Convolutional Neural Networks [30.732298624941738]
  We propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN. For each filter, we first evaluate the importance value of their input channels to identify the importance vectors. Using the resulting emphdata-dependent centroids, we prune the less important connections, which implicitly minimizes the accuracy loss of the pruning.
  arXiv  Detail & Related papers  (2020-09-29T06:24:32Z)
• Dependency Aware Filter Pruning [74.69495455411987]
  Pruning a proportion of unimportant filters is an efficient way to mitigate the inference cost. Previous work prunes filters according to their weight norms or the corresponding batch-norm scaling factors. We propose a novel mechanism to dynamically control the sparsity-inducing regularization so as to achieve the desired sparsity.
  arXiv  Detail & Related papers  (2020-05-06T07:41:22Z)

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.