REVIEW 34 cited by
A Survey on Oversmoothing in Graph Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
A Survey on Oversmoothing in Graph Neural Networks
read the original abstract
Node features of graph neural networks (GNNs) tend to become more similar with the increase of the network depth. This effect is known as over-smoothing, which we axiomatically define as the exponential convergence of suitable similarity measures on the node features. Our definition unifies previous approaches and gives rise to new quantitative measures of over-smoothing. Moreover, we empirically demonstrate this behavior for several over-smoothing measures on different graphs (small-, medium-, and large-scale). We also review several approaches for mitigating over-smoothing and empirically test their effectiveness on real-world graph datasets. Through illustrative examples, we demonstrate that mitigating over-smoothing is a necessary but not sufficient condition for building deep GNNs that are expressive on a wide range of graph learning tasks. Finally, we extend our definition of over-smoothing to the rapidly emerging field of continuous-time GNNs.
Forward citations
Cited by 34 Pith papers
-
Grothendieck Graph Neural Networks Framework: An Algebraic Platform for Crafting Topology-Aware GNNs
GkGNN extends GNN message passing from neighborhoods to covers via category theory, with the Sieve Neural Networks instantiation achieving zero failures on SRG, CSL, and BREC isomorphism benchmarks.
-
AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network
AGDN is a new GNN framework using a MixScore matrix and anisotropic graph diffusion to outperform prior methods on TSP instances across sizes and distributions.
-
Learn When and Where to Connect: Adaptive Virtual Nodes for Dynamic Message Passing on Graphs
MAVN adaptively selects and connects virtual nodes in MPNNs via learned dual-perspective preferences, proves it can realize any connectivity pattern, and reports up to 46.5% gains over backbones on nine datasets.
-
CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection
CAMERA is an ego-decoupled mixture-of-experts model with context-informed gating and one-class objectives for unsupervised fraud detection in text-attributed graphs facing semantic camouflage.
-
From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics
RAM augments relational graph models with attribute-semantic retrieval via random-walk documents and two contrastive augmentations (ATRA, ETRA) to achieve state-of-the-art results on five real-world databases.
-
Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
MbaGCN combines message aggregation, selective state space transitions, and node state prediction to create a more scalable deep graph convolutional network.
-
A Spectral Theory of Normalized Corrected GNN Propagation
Proves high-probability exact recovery in binary CSBM after O(log n) steps of corrected normalized propagation in dense polylog regime under graph-signal and feature-SNR conditions.
-
Attention mechanism for scalable mesh-based neural surrogates of free-surface fluids
Self-attention mechanisms are used to build mesh-preserving neural surrogates that approximate PFEM dynamics for free-surface flows, delivering accurate transient predictions and improved scalability on 2D and 3D benchmarks.
-
Early-Exit Graph Neural Networks for Link Prediction
Early-exit GNNs for link prediction move the speed-quality Pareto frontier on the HeaRT benchmark by allowing implicit early exiting without auxiliary losses.
-
Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport
TSNN equips temporal graphs with per-node time-varying orthogonal frames, explicit transport, and a geometric-residual decoder, delivering competitive or superior link prediction on benchmarks plus theoretical guarant...
-
Beyond Instance-Level Alignment and Uniformity: Semantic Factor Learning for Collaborative Filtering
SaFeAU augments collaborative filtering with semantic factor disentanglement and matching to reduce false negatives and capture higher-order signals via matrix factorization.
-
Self-supervised Adversarial Purification for Graph Neural Networks
GPR-GAE is a novel self-supervised graph auto-encoder purifier using multiple GPR filters and multi-step recovery that delivers state-of-the-art robustness for GNNs against structural attacks as a plug-and-play module.
-
Self-supervised Adversarial Purification for Graph Neural Networks
GPR-GAE is a novel self-supervised graph auto-encoder using multiple Generalized PageRank filters that serves as a plug-and-play purifier achieving state-of-the-art robustness for GNNs against structural attacks.
-
Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?
Deep ensembles fail to capture meaningful epistemic uncertainty in message-passing GNNs due to epistemic collapse where independently trained networks converge to similar predictions.
-
BrainDyn: A Sheaf Neural ODE for Generative Brain Dynamics
BrainDyn is a sheaf neural ODE model that encodes brain region activity history via LSTMs, projects states through restriction maps, and uses a sheaf Laplacian for message passing to generate continuous-time dynamics ...
-
Neural Point-Forms
Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and comp...
-
SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning
SACHI uses graph transformer convolutions on inter-agent coordination graphs to enrich partial-observation agents with content-dependent teammate information, yielding statistically significant gains over baselines in...
-
SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning
SACHI enriches agent representations via graph transformer convolutions over inter-agent graphs to enable holistic information integration, outperforming baselines across five cooperative tasks with statistical significance.
-
NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces
NSPOD is a multigrid-like deep operator network preconditioner that dramatically reduces Krylov solver iterations for linearized solid mechanics PDEs on unstructured meshes from CAD geometries.
-
NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces
NSPOD is a multigrid-like preconditioner using DeepONet-learned POD subspaces that dramatically cuts Krylov solver iterations for solid mechanics PDEs on unstructured CAD geometries, outperforming algebraic multigrid.
-
Robustness of Spatio-temporal Graph Neural Networks for Fault Location in Partially Observable Distribution Grids
Measured-only graph topologies enable STGNNs to achieve up to 11-point F1 gains and 6x faster training versus full-topology GNNs and RNN baselines for fault location in partially observable distribution grids.
-
Capacity-Controlled Global Attention for Graph Transformers
SigGate-GT applies sigmoid gates to attention outputs in graph transformers to reduce over-smoothing, matching prior best on ZINC and setting new SOTA on ogbg-molhiv with gains over GraphGPS.
-
Learning from Historical Activations in Graph Neural Networks
HISTOGRAPH applies unified layer-wise attention followed by node-wise attention over historical GNN activations to improve graph classification, especially in deep models.
-
Parameter-Efficient Conditioning for Material Generalization in Graph-Based Simulators
FiLM conditioning targeted at early message-passing layers lets pretrained GNS models generalize to new material properties using only 12 trajectories, a 5-fold data reduction versus multi-task baselines.
-
Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation
A Multi-L KG and Quest-GNN with question-adaptive intra/inter-level message passing and synthesized pre-training data improves multi-hop RAG performance up to 33.8% on high-hop questions.
-
Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
BES is an adaptive contrastive learning plug-in for GNNs that shapes boundary embeddings to disentangle spurious structural correlations, yielding 3.3% average gains in node classification.
-
S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
S³GNN mitigates oversquashing in message-passing networks via lightweight global mixing without strong prior assumptions, yielding up to 10x error reduction and 50% fewer parameters across multiple domains.
-
Quantile-Free Uncertainty Quantification in Graph Neural Networks
QpiGNN provides a quantile-free dual-head architecture for GNN uncertainty quantification that directly optimizes coverage and interval width, yielding 22% higher coverage and 50% narrower intervals than baselines on ...
-
Robustness of Spatio-temporal Graph Neural Networks for Fault Location in Partially Observable Distribution Grids
Measured-only STGNNs (RGATv2, RGSAGE) achieve up to 11 F1 points higher and 6x faster training than RNN baselines for fault location on the IEEE 123-bus feeder under partial observability.
-
From Load Tests to Live Streams: Graph Embedding-Based Anomaly Detection in Microservice Architectures
A GCN-GAE model learns node embeddings from directed weighted microservice graphs to flag anomalies via cosine similarity between load-test and live-event representations, with a synthetic injection framework reportin...
-
xAI-Drop: Don't Use What You Cannot Explain
xAI-Drop introduces an explainability-based topological dropping regularizer for GNNs that outperforms state-of-the-art dropping methods in accuracy and explanation quality on real-world datasets.
-
Ramanujan Graph Rewiring with Non Negative Resistance Curvature
Introduces Ramanujan Propagation as a graph rewiring method for GNNs that leverages Ramanujan graphs to ensure non-negative resistance curvature while preserving local connectivity and outperforming prior rewiring techniques.
-
Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
A survey reviewing graph rewiring methods that modify topology to mitigate over-squashing and over-smoothing in GNNs.
-
Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
A survey compiling graph rewiring techniques for mitigating over-squashing and over-smoothing in GNNs.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.