paper-with-me

Papers

Gradformer: Graph Transformer with Exponential Decay

2024-04-24 · Chuang Liu, Zelin Yao, Yibing Zhan, Xueqi Ma, Shirui Pan, Wenbin Hu

Graph Transformers (GTs) have demonstrated their advantages across a wide range of tasks. However, the self-attention mechanism in GTs overlooks the graph's inductive biases, particularly biases related to structure, which are crucial for the graph tasks. Although some methods utilize positional encoding and attention bias to model inductive biases, their effectiveness is still suboptimal analytically. Therefore, this paper presents Gradformer, a method innovatively integrating GT with the intrinsic inductive bias by applying an exponential decay mask to the attention matrix. Specifically, the values in the decay mask matrix diminish exponentially, correlating with the decreasing node proximities within the graph structure. This design enables Gradformer to retain its ability to capture information from distant nodes while focusing on the graph's local details. Furthermore, Gradformer introduces a learnable constraint into the decay mask, allowing different attention heads to learn distinct decay masks. Such an design diversifies the attention heads, enabling a more effective assimilation of diverse structural information within the graph. Extensive experiments on various benchmarks demonstrate that Gradformer consistently outperforms the Graph Neural Network and GT baseline models in various graph classification and regression tasks. Additionally, Gradformer has proven to be an effective method for training deep GT models, maintaining or even enhancing accuracy compared to shallow models as the network deepens, in contrast to the significant accuracy drop observed in other GT models.Codes are available at \url{https://github.com/LiuChuang0059/Gradformer}.

📄 PDF Abstract BibTeX arXiv:2404.15729

Code (1)

liuchuang0059/gradformer 공식 구현 pytorch

Tasks

Graph ClassificationGraph Neural NetworkInductive Bias

Methods 이 논문이 사용한 방법론

GTS 설명 없음
Exponential Decay Exponential Decay is a learning rate schedule where we decay the learning rate with more iterations using an exponential function: $$ \text{lr} =…
Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Rethinking the long-range dependency in Mamba/SSM and transformer models

2025-09-04 · Cong Ma, Kayvan Najarian arxiv

Long-range dependency is one of the most desired properties of recent sequence models such as state-space models (particularly Mamba) and transformer models. New model architectures are being actively developed and bench…

Transformer-Based Multi-Agent Reinforcement Learning for Networked Systems with Long-Range Interactions

2025-11-17 · Vidur Sinha, Muhammed Ustaomeroglu, Guannan Qu arxiv

Multi-agent reinforcement learning (MARL) has shown promise for large-scale network control, yet existing methods face two major limitations. First, they typically rely on an exponential decay property of agent interacti…

Multi-agent Reinforcement Learning

Training-Free ANN-to-SNN Conversion for High-Performance Spiking Transformer

2025-08-11 · Jingya Wang, Xin Deng, Wenjie Wei, Dehao Zhang 외 arxiv

Leveraging the event-driven paradigm, Spiking Neural Networks (SNNs) offer a promising approach for energy-efficient Transformer architectures.While ANN-to-SNN conversion avoids the high training cost of directly trained…

How to set AdamW's weight decay as you scale model and dataset size

2024-05-22 · Xi Wang, Laurence Aitchison

The scaling of the optimal AdamW weight decay hyperparameter with model and dataset size is critical as we seek to build larger models, but is poorly understood. We show that weights learned by AdamW can be understood as…

LeetDecoding: A PyTorch Library for Exponentially Decaying Causal Linear Attention with CUDA Implementations

2025-01-05 · Jiaping Wang, Simiao Zhang, Qiao-Chu He, Yifan Chen

The machine learning and data science community has made significant while dispersive progress in accelerating transformer-based large language models (LLMs), and one promising approach is to replace the original causal …

GPU