No article text was recorded for this version.
graph over-smoothing (over-smoothing)
Version 1 of 12,138 papers2,688 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Power of Graph Convolutional Networks to Distinguish Random Graph Models
- Blog: Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory
- Blog: On Asymptotic Behaviors of Graph CNNs from Dynamical Systems Perspective
- Blog: ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning
- Blog: Fundamental Limits of Deep Graph Convolutional Networks
- Blog: Residual connections provably mitigate oversmoothing in graph neural networks
- Blog: A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks
- Blog: Zero-One Laws of Graph Neural Networks
- Blog: Graph Neural Networks as Gradient Flows
- Blog: SkipNode: On Alleviating Over-smoothing for Deep Graph Convolutional Networks
- Blog: Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory
- Blog: A Note on Over-Smoothing for Graph Neural Networks
- Blog: Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning
- Blog: Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors
- Blog: Representation Learning on Graphs with Jumping Knowledge Networks
- Blog: The Power of Graph Convolutional Networks to Distinguish Random Graph Models
- Blog: Representation Learning on Graphs with Jumping Knowledge Networks
- Blog: Towards Deep Attention in Graph Neural Networks: Problems and Remedies
- Blog: From Community to Role-based Graph Embeddings
- Blog: Solving Oversmoothing in GNNs via Nonlocal Message Passing: Algebraic Smoothing and Depth Scalability
- Blog: Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
- Blog: Scaling Up, Scaling Deep: Blockwise Graph Contrastive Learning
- Blog: Addressing Over-Smoothing in Graph Neural Networks via Deep Supervision
- Blog: Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
- Blog: Towards Deep Attention in Graph Neural Networks: Problems and Remedies
- Blog: A Survey on Oversmoothing in Graph Neural Networks
- Blog: Using Graph Attention Network and Graph Convolutional Network to Explore Human CircRNA–Disease Associations Based on Multi-Source Data
- Blog: Isolation Graph Kernel
- Blog: Centered Self-attention Layers
- Blog: Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective
- Blog: Graph Neural Aggregation-diffusion with Metastability
- Blog: Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module
- Blog: Understanding and Tackling Over-Dilution in Graph Neural Networks
- Blog: Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
- Blog: From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach
- Blog: Poisson Kernel Avoiding Self-Smoothing in Graph Convolutional Networks
- Blog: SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation
- Blog: DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations
- Blog: Analysis of Graph Neural Networks with Theory of Markov Chains
- Blog: Memory-Augmented Relation Network for Few-Shot Learning
- Blog: Layer-to-Layer Knowledge Mixing in Graph Neural Network for Chemical Property Prediction
- Blog: A Message Passing Perspective on Learning Dynamics of Contrastive Learning
- Blog: Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
- Blog: Scaling Graph Convolutions for Mobile Vision
- Blog: Prediction model of short-term passenger flow of urban rail transit trains integrating temporal and spatial features
- Blog: Network representation learning: A macro and micro view
- Blog: Domain Adaptive Unfolded Graph Neural Networks
- Blog: Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution
- Blog: ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning
- Blog: Preserving Node Distinctness in Graph Autoencoders via Similarity Distillation
- Blog: From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach
- Blog: Very Deep Graph Neural Networks Via Noise Regularisation
- Blog: PairNorm: Tackling Oversmoothing in GNNs
- Blog: The Power of Graph Convolutional Networks to Distinguish Random Graph Models: Short Version
- Blog: Rethinking Functional Brain Connectome Analysis: Do Graph Deep Learning Models Help?
- Blog: Relevant Region Prediction for Crowd Counting
- Blog: Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
- Blog: Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks
- Blog: Diving Performance Analysis with 3D Motion Knowledge Hypergraphs
- Blog: Multiplex Heterogeneous Graph Convolutional Network
Showing 60 of 2,138 papers.
History & citation
Current · Permanent link
- Dense Connectivity in Deep Graph Convolutional Networks merged into this direction (53% overlap)
- Topology Adaptive Deep Graph Neural Networks merged into this direction (72% overlap)
- Local Subgraph Isolation for Deep Graph Networks merged into this direction (50% overlap)
- Balancing Attraction and Repulsion in Deep Graph Propagation merged into this direction (90% overlap)
- Preserving Dirichlet Energy in Deep Graph Neural Networks merged into this direction (80% overlap)
- Infinite Depth Graph Neural Networks merged into this direction (65% overlap)
- Feature Anchoring for Deep Graph Neural Networks merged into this direction (89% overlap)
- Preserving Node Identity in Deep Graph Neural Networks merged into this direction (64% overlap)
- Preventing Over-smoothing in Deep Graph Neural Networks merged into this direction (100% overlap)
- Counteracting Feature Homogenization in Deep Graph Neural Networks merged into this direction (81% overlap)
- Graph Neural Tangent Kernels and Infinite Width Limits merged into this direction (59% overlap)
- Scaling Graph Neural Networks Beyond Shallow Architectures merged into this direction (66% overlap)
- Graph Sparsification to Mitigate Over-smoothing in Deep Networks merged into this direction (70% overlap)
- Addressing Feature Homogenization in Deep Graph Neural Networks merged into this direction (82% overlap)
- Decoupling Feature Transformation from Graph Propagation merged into this direction (61% overlap)
- Second Order Wave Dynamics for Deep Graph Networks merged into this direction (75% overlap)
- Optimizing Gradient Propagation for Deep Graph Networks merged into this direction (51% overlap)
- Improving Generalization for Deep Graph Neural Networks merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_graph_over_smoothing_over_smoothing_644f8af5,
title = {graph over-smoothing (over-smoothing)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/graph-over-smoothing-over-smoothing/rdr_644f8af5ba6947638795f805b90d26b4},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_graph_over_smoothing_over_smoothing_644f8af5_v1,
title = {graph over-smoothing (over-smoothing)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/graph-over-smoothing-over-smoothing/rdr_644f8af5ba6947638795f805b90d26b4/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}