Search Results for author: Rex Ying

Found 24 papers, 19 papers with code

GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks

1 code implementation20 Jun 2022 Kenza Amara, Rex Ying, Zitao Zhang, Zhihao Han, Yinan Shan, Ulrik Brandes, Sebastian Schemm, Ce Zhang

As GNN models are deployed to more mission-critical applications, we are in dire need for a common evaluation protocol of explainability methods of GNNs.

Node Classification

Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator

no code implementations15 Jun 2022 Tailin Wu, Qinchen Wang, Yinan Zhang, Rex Ying, Kaidi Cao, Rok Sosič, Ridwan Jalali, Hassan Hamam, Marko Maucec, Jure Leskovec

To model complex reservoir dynamics at both local and global scale, HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure.

Decision Making

Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020

1 code implementation6 Apr 2022 Zhen Xu, Lanning Wei, Huan Zhao, Rex Ying, Quanming Yao, Wei-Wei Tu, Isabelle Guyon

Researchers naturally adopt Automated Machine Learning on Graph Learning, aiming to reduce the human effort and achieve generally top-performing GNNs, but their methods focus more on the architecture search.

Graph Learning Neural Architecture Search +1

Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones

1 code implementation NeurIPS 2021 Yushi Bai, Rex Ying, Hongyu Ren, Jure Leskovec

Here we present ConE (Cone Embedding), a KG embedding model that is able to simultaneously model multiple hierarchical as well as non-hierarchical relations in a knowledge graph.

Ancestor-descendant prediction Knowledge Graph Completion +1

Neural Distance Embeddings for Biological Sequences

1 code implementation NeurIPS 2021 Gabriele Corso, Rex Ying, Michal Pándy, Petar Veličković, Jure Leskovec, Pietro Liò

The development of data-dependent heuristics and representations for biological sequences that reflect their evolutionary distance is critical for large-scale biological research.

Multiple Sequence Alignment

Local Augmentation for Graph Neural Networks

1 code implementation8 Sep 2021 Songtao Liu, Rex Ying, Hanze Dong, Lanqing Li, Tingyang Xu, Yu Rong, Peilin Zhao, Junzhou Huang, Dinghao Wu

To address this, we propose a simple and efficient data augmentation strategy, local augmentation, to learn the distribution of the node features of the neighbors conditioned on the central node's feature and enhance GNN's expressive power with generated features.

Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks

1 code implementation24 Jun 2021 Jiaqing Xie, Rex Ying

In this paper, we introuduce graph feature to feature (Fea2Fea) prediction pipelines in a low dimensional space to explore some preliminary results on structural feature correlation, which is based on graph neural network.

Graph Classification Node Classification +1

Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification

no code implementations NAACL 2021 Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He, BoWen Zhou

Recent work on aspect-level sentiment classification has demonstrated the efficacy of incorporating syntactic structures such as dependency trees with graph neural networks(GNN), but these approaches are usually vulnerable to parsing errors.

Ensemble Learning General Classification +1

Identity-aware Graph Neural Networks

1 code implementation25 Jan 2021 Jiaxuan You, Jonathan Gomes-Selman, Rex Ying, Jure Leskovec

However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and shortest path distances, and cannot differentiate between different d-regular graphs.

Graph Classification Graph Property Prediction +2

Design Space for Graph Neural Networks

1 code implementation NeurIPS 2020 Jiaxuan You, Rex Ying, Jure Leskovec

However, current research focuses on proposing and evaluating specific architectural designs of GNNs, as opposed to studying the more general design space of GNNs that consists of a Cartesian product of different design dimensions, such as the number of layers or the type of the aggregation function.

Multi-hop Attention Graph Neural Network

1 code implementation29 Sep 2020 Guangtao Wang, Rex Ying, Jing Huang, Jure Leskovec

Currently, at every layer, attention is computed between connected pairs of nodes and depends solely on the representation of the two nodes.

Graph Representation Learning Knowledge Graph Completion +1

Learning to Simulate Complex Physics with Graph Networks

9 code implementations ICML 2020 Alvaro Sanchez-Gonzalez, Jonathan Godwin, Tobias Pfaff, Rex Ying, Jure Leskovec, Peter W. Battaglia

Here we present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and deformable materials interacting with one another.

Hyperbolic Graph Convolutional Neural Networks

1 code implementation NeurIPS 2019 Ines Chami, Rex Ying, Christopher Ré, Jure Leskovec

Here we propose Hyperbolic Graph Convolutional Neural Network (HGCN), the first inductive hyperbolic GCN that leverages both the expressiveness of GCNs and hyperbolic geometry to learn inductive node representations for hierarchical and scale-free graphs.

Link Prediction Node Classification

Improving Graph Attention Networks with Large Margin-based Constraints

no code implementations25 Oct 2019 Guangtao Wang, Rex Ying, Jing Huang, Jure Leskovec

Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs.

Graph Attention Representation Learning

Neural Execution of Graph Algorithms

no code implementations ICLR 2020 Petar Veličković, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell

Graph Neural Networks (GNNs) are a powerful representational tool for solving problems on graph-structured inputs.

Position-aware Graph Neural Networks

2 code implementations11 Jun 2019 Jiaxuan You, Rex Ying, Jure Leskovec

Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs.

Community Detection Link Prediction

Redundancy-Free Computation Graphs for Graph Neural Networks

no code implementations9 Jun 2019 Zhihao Jia, Sina Lin, Rex Ying, Jiaxuan You, Jure Leskovec, Alex Aiken

Graph Neural Networks (GNNs) are based on repeated aggregations of information across nodes' neighbors in a graph.

GNNExplainer: Generating Explanations for Graph Neural Networks

10 code implementations NeurIPS 2019 Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec

We formulate GNNExplainer as an optimization task that maximizes the mutual information between a GNN's prediction and distribution of possible subgraph structures.

Explainable artificial intelligence Graph Classification +1

Hierarchical Graph Representation Learning with Differentiable Pooling

12 code implementations NeurIPS 2018 Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, Jure Leskovec

Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings, and achieved state-of-the-art results in tasks such as node classification and link prediction.

General Classification Graph Classification +3

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation

2 code implementations NeurIPS 2018 Jiaxuan You, Bowen Liu, Rex Ying, Vijay Pande, Jure Leskovec

Generating novel graph structures that optimize given objectives while obeying some given underlying rules is fundamental for chemistry, biology and social science research.

Graph Generation Molecular Graph Generation

Graph Convolutional Neural Networks for Web-Scale Recommender Systems

3 code implementations6 Jun 2018 Rex Ying, Ruining He, Kai-Feng Chen, Pong Eksombatchai, William L. Hamilton, Jure Leskovec

We develop a data-efficient Graph Convolutional Network (GCN) algorithm PinSage, which combines efficient random walks and graph convolutions to generate embeddings of nodes (i. e., items) that incorporate both graph structure as well as node feature information.

Recommendation Systems

GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

2 code implementations ICML 2018 Jiaxuan You, Rex Ying, Xiang Ren, William L. Hamilton, Jure Leskovec

Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences.

Graph Generation

Representation Learning on Graphs: Methods and Applications

1 code implementation17 Sep 2017 William L. Hamilton, Rex Ying, Jure Leskovec

Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks.

Dimensionality Reduction Representation Learning

Inductive Representation Learning on Large Graphs

12 code implementations NeurIPS 2017 William L. Hamilton, Rex Ying, Jure Leskovec

Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions.

Graph Classification Graph Regression +3

Cannot find the paper you are looking for? You can Submit a new open access paper.