Picture for Shengjie Luo

Shengjie Luo

Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation

Jan 29, 2024
Viaarxiv icon

Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products

Add code
Jan 18, 2024
Viaarxiv icon

Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers

Feb 03, 2023
Figure 1 for Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
Figure 2 for Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
Figure 3 for Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
Figure 4 for Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
Viaarxiv icon

Rethinking the Expressive Power of GNNs via Graph Biconnectivity

Add code
Jan 23, 2023
Figure 1 for Rethinking the Expressive Power of GNNs via Graph Biconnectivity
Figure 2 for Rethinking the Expressive Power of GNNs via Graph Biconnectivity
Figure 3 for Rethinking the Expressive Power of GNNs via Graph Biconnectivity
Figure 4 for Rethinking the Expressive Power of GNNs via Graph Biconnectivity
Viaarxiv icon

One Transformer Can Understand Both 2D & 3D Molecular Data

Add code
Oct 04, 2022
Figure 1 for One Transformer Can Understand Both 2D & 3D Molecular Data
Figure 2 for One Transformer Can Understand Both 2D & 3D Molecular Data
Figure 3 for One Transformer Can Understand Both 2D & 3D Molecular Data
Figure 4 for One Transformer Can Understand Both 2D & 3D Molecular Data
Viaarxiv icon

Your Transformer May Not be as Powerful as You Expect

Add code
May 26, 2022
Figure 1 for Your Transformer May Not be as Powerful as You Expect
Figure 2 for Your Transformer May Not be as Powerful as You Expect
Figure 3 for Your Transformer May Not be as Powerful as You Expect
Figure 4 for Your Transformer May Not be as Powerful as You Expect
Viaarxiv icon

An Empirical Study of Graphormer on Large-Scale Molecular Modeling Datasets

Add code
Mar 14, 2022
Figure 1 for An Empirical Study of Graphormer on Large-Scale Molecular Modeling Datasets
Figure 2 for An Empirical Study of Graphormer on Large-Scale Molecular Modeling Datasets
Figure 3 for An Empirical Study of Graphormer on Large-Scale Molecular Modeling Datasets
Figure 4 for An Empirical Study of Graphormer on Large-Scale Molecular Modeling Datasets
Viaarxiv icon

Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets

Add code
Mar 09, 2022
Figure 1 for Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets
Figure 2 for Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets
Figure 3 for Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets
Viaarxiv icon

Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding

Add code
Jun 23, 2021
Figure 1 for Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
Figure 2 for Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
Figure 3 for Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
Figure 4 for Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
Viaarxiv icon

First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track

Jun 20, 2021
Figure 1 for First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track
Figure 2 for First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track
Figure 3 for First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track
Figure 4 for First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track
Viaarxiv icon