activity
20162024
most citedDo Transformers Really Perform Bad for Graph Representation?

132 citations · 345 across the 20 of their papers we have counts for

collaborators
Showing 2021Show all

5 papers · 1 filter

cs.LG2021

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

Chengxuan Ying, Mingqi Yang, Shuxin Zheng +7

In this technical report, we present our solution of KDD Cup 2021 OGB Large-Scale Challenge - PCQM4M-LSC Track. We adopt Graphormer and ExpC as our basic models. We train each mode…

cs.LG2021★ 7 cited

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

Shengjie Luo, Shanda Li, Tianle Cai +6

The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the…

cs.LG2021★ 132 cited

Do Transformers Really Perform Bad for Graph Representation?

Chengxuan Ying, Tianle Cai, Shengjie Luo +5

The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance…

cs.PL2021★ 1 cited

How could Neural Networks understand Programs?

Dinglan Peng, Shuxin Zheng, Yatao Li +3

Semantic understanding of programs is a fundamental problem for programming language processing (PLP). Recent works that learn representations of code based on pre-training techniq…

cs.CL2021★ 3 cited

Revisiting Language Encoding in Learning Multilingual Representations

Shengjie Luo, Kaiyuan Gao, Shuxin Zheng +4

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a le…