Alert button
Picture for Keyulu Xu

Keyulu Xu

Alert button

Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth

May 26, 2021
Keyulu Xu, Mozhi Zhang, Stefanie Jegelka, Kenji Kawaguchi

Figure 1 for Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Figure 2 for Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Figure 3 for Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Figure 4 for Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Viaarxiv icon

Noisy Labels Can Induce Good Representations

Dec 23, 2020
Jingling Li, Mozhi Zhang, Keyulu Xu, John P. Dickerson, Jimmy Ba

Figure 1 for Noisy Labels Can Induce Good Representations
Figure 2 for Noisy Labels Can Induce Good Representations
Figure 3 for Noisy Labels Can Induce Good Representations
Figure 4 for Noisy Labels Can Induce Good Representations
Viaarxiv icon

Graph Adversarial Networks: Protecting Information against Adversarial Attacks

Oct 07, 2020
Peiyuan Liao, Han Zhao, Keyulu Xu, Tommi Jaakkola, Geoffrey Gordon, Stefanie Jegelka, Ruslan Salakhutdinov

Figure 1 for Graph Adversarial Networks: Protecting Information against Adversarial Attacks
Figure 2 for Graph Adversarial Networks: Protecting Information against Adversarial Attacks
Figure 3 for Graph Adversarial Networks: Protecting Information against Adversarial Attacks
Figure 4 for Graph Adversarial Networks: Protecting Information against Adversarial Attacks
Viaarxiv icon

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks

Oct 01, 2020
Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka

Figure 1 for How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Figure 2 for How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Figure 3 for How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Figure 4 for How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Viaarxiv icon

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

Sep 07, 2020
Tianle Cai, Shengjie Luo, Keyulu Xu, Di He, Tie-yan Liu, Liwei Wang

Figure 1 for GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
Figure 2 for GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
Figure 3 for GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
Figure 4 for GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
Viaarxiv icon

Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization

Jun 05, 2019
Mozhi Zhang, Keyulu Xu, Ken-ichi Kawarabayashi, Stefanie Jegelka, Jordan Boyd-Graber

Figure 1 for Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
Figure 2 for Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
Figure 3 for Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
Figure 4 for Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
Viaarxiv icon

What Can Neural Networks Reason About?

May 31, 2019
Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka

Figure 1 for What Can Neural Networks Reason About?
Figure 2 for What Can Neural Networks Reason About?
Figure 3 for What Can Neural Networks Reason About?
Figure 4 for What Can Neural Networks Reason About?
Viaarxiv icon