Cover Image

gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Blayney, Hugh, Arroyo, Álvaro, Dong, Xiaowen, Bronstein, Michael M.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning
by: Arroyo, Álvaro, et al.
Published: (2025)

A Mechanistic Analysis of Looped Reasoning Language Models
by: Blayney, Hugh, et al.
Published: (2026)

Can Graph Foundation Models Generalize Over Architecture?
by: Gutteridge, Benjamin, et al.
Published: (2026)

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
by: Attali, Hugo, et al.
Published: (2024)

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
by: Attali, Hugo, et al.
Published: (2026)

Improving Spatio-Temporal Residual Error Propagation by Mitigating Over-Squashing
by: Moghadas, Seyed Mohamad, et al.
Published: (2026)

Adaptive Graph Rewiring to Mitigate Over-Squashing in Mesh-Based GNNs for Fluid Dynamics Simulations
by: Seo, Sangwoo, et al.
Published: (2025)

Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
by: Queipo-de-Llano, Enrique, et al.
Published: (2025)

Effective Resistance Rewiring: A Simple Topological Correction for Over-Squashing
by: Miquel-Oliver, Bertran, et al.
Published: (2026)

Rough Transformers for Continuous and Efficient Time-Series Modelling
by: Moreno-Pino, Fernando, et al.
Published: (2024)

Over-squashing in Spatiotemporal Graph Neural Networks
by: Marisca, Ivan, et al.
Published: (2025)

On Measuring Long-Range Interactions in Graph Neural Networks
by: Bamberger, Jacob, et al.
Published: (2025)

Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement
by: Liang, Huidong, et al.
Published: (2025)

Effective Sample Size and Generalization Bounds for Temporal Networks
by: Gahtan, Barak, et al.
Published: (2025)

How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation
by: You, Zinuo, et al.
Published: (2025)

Mathematical Foundations of Geometric Deep Learning
by: Borde, Haitz Sáez de Ocáriz, et al.
Published: (2025)

Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning
by: Zhu, Ting, et al.
Published: (2024)

Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
by: Dai, Juntao, et al.
Published: (2025)

Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature
by: Fesser, Lukas, et al.
Published: (2023)

Supercharging Graph Transformers with Advective Diffusion
by: Wu, Qitian, et al.
Published: (2023)

HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs
by: Huang, Xingyue, et al.
Published: (2025)

Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage
by: Yamanaka, Hiroaki, et al.
Published: (2026)

Cooperative Graph Neural Networks
by: Finkelshtein, Ben, et al.
Published: (2023)

packetLSTM: Dynamic LSTM Framework for Streaming Data with Varying Feature Space
by: Agarwal, Rohit, et al.
Published: (2024)

LLMs can hide text in other text of the same length
by: Norelli, Antonio, et al.
Published: (2025)

Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
by: Liang, Langzhang, et al.
Published: (2025)

Enhancing Spatiotemporal Networks with xLSTM: A Scalar LSTM Approach for Cellular Traffic Forecasting
by: Ali, Khalid, et al.
Published: (2025)

xLSTM: Extended Long Short-Term Memory
by: Beck, Maximilian, et al.
Published: (2024)

Heterogeneous Graph Structure Learning through the Lens of Data-generating Processes
by: Jiang, Keyue, et al.
Published: (2025)

On the Importance of Task Complexity in Evaluating LLM-Based Multi-Agent Systems
by: Tang, Bohan, et al.
Published: (2025)

Bures-Wasserstein Flow Matching for Graph Generation
by: Jiang, Keyue, et al.
Published: (2025)

A Characterization Theorem for Equivariant Networks with Point-wise Activations
by: Pacini, Marco, et al.
Published: (2024)

Separation Power of Equivariant Neural Networks
by: Pacini, Marco, et al.
Published: (2024)

Predicting Stock Prices with FinBERT-LSTM: Integrating News Sentiment Analysis
by: Gu, Wenjun, et al.
Published: (2024)

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
by: He, Shwai, et al.
Published: (2025)

Network Level Spatial Temporal Traffic State Forecasting with Hierarchical-Attention-LSTM (HierAttnLSTM)
by: Zhang, Tianya
Published: (2022)

Link Prediction with Relational Hypergraphs
by: Huang, Xingyue, et al.
Published: (2024)

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
by: Dabas, Mahavir, et al.
Published: (2025)

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy
by: Jiang, Eric Hanchen, et al.
Published: (2025)

Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
by: Song, Haobo, et al.
Published: (2024)