Image de couverture de livre

Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Roth, Andreas, Bause, Franka, Kriege, Nils M., Liebig, Thomas
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks
par: Roth, Andreas, et autres
Publié: (2023)

XIMP: Cross Graph Inter-Message Passing for Molecular Property Prediction
par: Ehrlich, Anatol, et autres
Publié: (2026)

On the Two Sides of Redundancy in Graph Neural Networks
par: Bause, Franka, et autres
Publié: (2023)

What Can We Learn From MIMO Graph Convolutions?
par: Roth, Andreas, et autres
Publié: (2025)

Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
par: Kummer, Lorenz, et autres
Publié: (2025)

Efficient Mixed Precision Quantization in Graph Neural Networks
par: Moustafa, Samir, et autres
Publié: (2025)

On the Relationship Between Robustness and Expressivity of Graph Neural Networks
par: Kummer, Lorenz, et autres
Publié: (2025)

Boosting Graph Neural Network Expressivity with Learnable Lanczos Constraints
par: Azizi, Niloofar, et autres
Publié: (2024)

Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?
par: Bause, Franka, et autres
Publié: (2026)

Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks
par: Kummer, Lorenz, et autres
Publié: (2025)

On dimensionality of feature vectors in MPNNs
par: Bravo, César, et autres
Publié: (2024)

Visualization and Analysis of the Loss Landscape in Graph Neural Networks
par: Moustafa, Samir, et autres
Publié: (2025)

On the Expressive Power of Sparse Geometric MPNNs
par: Sverdlov, Yonatan, et autres
Publié: (2024)

Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding
par: Haritz, Pierre, et autres
Publié: (2024)

AALF: Almost Always Linear Forecasting
par: Jakobs, Matthias, et autres
Publié: (2024)

Are Graph Transformers Necessary? Efficient Long-Range Message Passing with Fractal Nodes in MPNNs
par: Choi, Jeongwhan, et autres
Publié: (2025)

Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse
par: Alman, Josh, et autres
Publié: (2025)

Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent
par: Kummer, Lorenz, et autres
Publié: (2023)

Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity
par: Wu, Fei, et autres
Publié: (2026)

Towards Understanding and Avoiding Limitations of Convolutions on Graphs
par: Roth, Andreas
Publié: (2026)

Using Petri Nets as an Integrated Constraint Mechanism for Reinforcement Learning Tasks
par: Sachweh, Timon, et autres
Publié: (2024)

The Inlet Rank Collapse in Implicit Neural Representations: Diagnosis and Unified Remedy
par: Zheng, Jianqiao, et autres
Publié: (2026)

What drives performance in molecular MPNNs? An operator-level factorial benchmark
par: Jiao, Panyu, et autres
Publié: (2026)

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
par: Arefin, Md Rifat, et autres
Publié: (2024)

Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval
par: Alomari, Hani, et autres
Publié: (2025)

Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation
par: Mahon, Louis, et autres
Publié: (2023)

Demystifying MPNNs: Message Passing as Merely Efficient Matrix Multiplication
par: Jiang, Qin, et autres
Publié: (2025)

ICE-T: A Multi-Faceted Concept for Teaching Machine Learning
par: Krone, Hendrik, et autres
Publié: (2024)

Explaining and Preventing Alignment Collapse in Iterative RLHF
par: Gauthier, Etienne, et autres
Publié: (2026)

Golden Ratio Weighting Prevents Model Collapse
par: He, Hengzhi, et autres
Publié: (2025)

Countering Multi-modal Representation Collapse through Rank-targeted Fusion
par: Kim, Seulgi, et autres
Publié: (2025)

IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning
par: Almpanakis, Konstantinos, et autres
Publié: (2026)

Low-Rank Learning by Design: the Role of Network Architecture and Activation Linearity in Gradient Rank Collapse
par: Baker, Bradley T., et autres
Publié: (2024)

Preventing Model Collapse in Gaussian Process Latent Variable Models
par: Li, Ying, et autres
Publié: (2024)

Feature Normalization Prevents Collapse of Non-contrastive Learning Dynamics
par: Bao, Han
Publié: (2023)

The Persistence of Neural Collapse Despite Low-Rank Bias
par: Garrod, Connall, et autres
Publié: (2024)

ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning
par: Yuan, Chaohao, et autres
Publié: (2025)

Simplifying the Theory on Over-Smoothing
par: Roth, Andreas
Publié: (2024)

Rank, Head-Channel Non-Identifiability, and Symmetry Breaking: A Precise Analysis of Representational Collapse in Transformers
par: Cirrincione, Giansalvo
Publié: (2026)

Two Facets of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
par: Li, Xunkai, et autres
Publié: (2025)