5 papers
Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs
Zichao Yue, Zhiru Zhang
Pre-propagation graph neural networks (PPGNNs) push all graph-dependent computation into a preprocessing step and train only on the resulting dense hop features, which makes them h…
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
Zichao Yue, Zhiru Zhang
Pre-propagation graph neural networks (PPGNNs) decouple node feature propagation from transformation: graph diffusion is performed once as preprocessing, and training reduces to de…
Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs
Zichao Yue, Chenhui Deng, Zhiru Zhang
Graph neural networks (GNNs) are widely used for learning node embeddings in graphs, typically adopting a message-passing scheme. This approach, however, leads to the neighbor expl…
Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference
Hongzheng Chen, Jiahao Zhang, Yixiao Du +5
Recent advancements in large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. The majorit…
Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
Chenhui Deng, Zichao Yue, Zhiru Zhang
Graph transformers (GTs) have emerged as a promising architecture that is theoretically more expressive than message-passing graph neural networks (GNNs). However, typical GT model…