S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning

• URL: http://arxiv.org/abs/2605.23467v1
• Date: Fri, 22 May 2026 10:26:41 GMT
• Title: S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
• Abstract summary: Message-passing neural networks (MPNNs) often suffer from an information bottleneck when capturing long-range dependencies.<n>We propose S$3$GNN, which mitigates oversquashing (OSQ) by lightweightly reintroducing omitted components.<n>Our experiments show that S$3$GNN achieves up to an order-of-magnitude error reduction with up to 50% fewer parameters.
• Score: 56.04227780048336
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Message-passing neural networks (MPNNs) often suffer from an information bottleneck when capturing long-range dependencies, leading to the oversquashing (OSQ) phenomenon. Alongside spatial connectivity enrichment (e.g., rewiring), recent studies have shown that spectral filtering can yield strong long-range learning outcomes, as spectral operators enable global information mixing that alleviates OSQ. These approaches achieve this either by stabilizing the Jacobian energies in deep propagation or by guaranteeing OSQ mitigation under strong theoretical assumptions. We revisit these conclusions and show that the associated Jacobian sensitivity lower bound is generally difficult to achieve in practice. We then propose S$^3$GNN, which mitigates OSQ without such restrictive assumptions by lightweightly reintroducing omitted components with substantially lower computational complexity, while standard stability constraints on feature transformations remain effective under our new dynamics. Extensive experiments across diverse domains (e.g., long-range benchmarks, KGQA, and mesh-based fluid dynamics) demonstrate that S$^3$GNN achieves up to an order-of-magnitude error reduction with up to 50\% fewer parameters. Our code can be found in https://github.com/EEthanShi/S3-GNN.git.

Related papers

• Quantile-Free Uncertainty Quantification in Graph Neural Networks [22.90804904063177]
  Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge.<n>We introduce Quantile-free Prediction Interval GNN (QpiGNN), a framework that builds on quantile regression (QR) to enable GNN-based UQ.<n>QpiGNN employs a dual-head architecture that decouples prediction and uncertainty, and is trained with label-only supervision through a quantile-free joint loss.
  arXiv  Detail & Related papers  (2026-05-06T12:44:54Z)
• Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting [78.96382179408054]
  We introduce bfLeGS, a framework that reformulates density control as a parameterized policy network optimized via Reinforcement Learning (RL)<n>To maintain computational tractability, we derive a closed-form solution that reduces the complexity of reward calculation from $O(N2)$ to $O(N)$.<n>Experiments on the Mip-NeRF 360, Tanks & Temples, and Deep Blending datasets demonstrate that bfLeGS significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-01T05:04:49Z)
• Lund Plane to Bloch (LP2B) Encoding for Object and Polarization Tagging with Quantum Jet Substructure [0.0]
  Jet substructure remains essential for addressing demanding and complementary challenges at the LHC and beyond.<n>We introduce the Lund Plane to Bloch (LP2B) encoding, designed to map a theoretically clean and robust representation of jet kinematics directly into qubit states.<n>We implement a Quantum Tree-Topology Network (QTTN) that embeds the hierarchical structure of the Lund tree.
  arXiv  Detail & Related papers  (2026-04-15T13:57:22Z)
• Data-Driven Deep MIMO Detection:Network Architectures and Generalization Analysis [50.20709408241935]
  This paper proposes inspecting the fully data-driven DeepSIC detection within a Network-of-MLPs architecture.<n>Within such an architecture, DeepSIC can be upgraded as a graph-based message-passing process using Graph Neural Networks (GNNs)<n>GNNSIC achieves excellent expressivity comparable to DeepSIC with substantially fewer trainable parameters.
  arXiv  Detail & Related papers  (2026-02-13T04:38:51Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Learning k-Level Structured Sparse Neural Networks Using Group Envelope Regularization [4.0554893636822]
  We introduce a novel approach to deploy large-scale Deep Neural Networks on constrained resources. The method speeds up inference time and aims to reduce memory demand and power consumption.
  arXiv  Detail & Related papers  (2022-12-25T15:40:05Z)
• Navigating Local Minima in Quantized Spiking Neural Networks [3.1351527202068445]
  Spiking and Quantized Neural Networks (NNs) are becoming exceedingly important for hyper-efficient implementations of Deep Learning (DL) algorithms. These networks face challenges when trained using error backpropagation, due to the absence of gradient signals when applying hard thresholds. This paper presents a systematic evaluation of a cosine-annealed LR schedule coupled with weight-independent adaptive moment estimation.
  arXiv  Detail & Related papers  (2022-02-15T06:42:25Z)
• Robust Graph Neural Networks via Probabilistic Lipschitz Constraints [7.359962178534361]
  Graph neural networks (GNNs) have recently been demonstrated to perform well on a variety of network-based tasks. GNNs are susceptible to shifts and perturbations on their inputs, which can include both node attributes and graph structure.
  arXiv  Detail & Related papers  (2021-12-14T17:33:32Z)
• AQD: Towards Accurate Fully-Quantized Object Detection [94.06347866374927]
  We propose an Accurate Quantized object Detection solution, termed AQD, to get rid of floating-point computation. Our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes.
  arXiv  Detail & Related papers  (2020-07-14T09:07:29Z)

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.