An Overview of Microsoft Academic Service (MAS) and Applications
- Arnab Sinha, Zhihong Shen, Kuansan Wang
- Computer ScienceThe Web Conference
- 18 May 2015
A knowledge driven, highly interactive dialog that seamlessly combines reactive search and proactive suggestion experience, and a proactive heterogeneous entity recommendation are demonstrated.
Heterogeneous Graph Transformer
- Ziniu Hu, Yuxiao Dong, Kuansan Wang, Yizhou Sun
- Computer ScienceThe Web Conference
- 3 March 2020
The proposed HGT model consistently outperforms all the state-of-the-art GNN baselines by 9–21 on various downstream tasks, and the heterogeneous mini-batch graph sampling algorithm—HGSampling—for efficient and scalable training.
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
- J. Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, Jie Tang
- Computer ScienceWeb Search and Data Mining
- 9 October 2017
The NetMF method offers significant improvements over DeepWalk and LINE for conventional network mining tasks and provides the theoretical connections between skip-gram based network embedding algorithms and the theory of graph Laplacian.
CORD-19: The Covid-19 Open Research Dataset
- Lucy Lu Wang, Kyle Lo, Sebastian Kohlmeier
- Computer ScienceNLPCOVID19
- 22 April 2020
The mechanics of dataset construction are described, highlighting challenges and key design decisions, an overview of how CORD-19 has been used, and several shared tasks built around the dataset are described.
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
- J. Qiu, Qibin Chen, Jie Tang
- Computer ScienceKnowledge Discovery and Data Mining
- 17 June 2020
Graph Contrastive Coding (GCC) is designed --- a self-supervised graph neural network pre-training framework --- to capture the universal network topological properties across multiple networks and leverage contrastive learning to empower graph neural networks to learn the intrinsic and transferable structural representations.
GPT-GNN: Generative Pre-Training of Graph Neural Networks
- Ziniu Hu, Yuxiao Dong, Kuansan Wang, Kai-Wei Chang, Yizhou Sun
- Computer ScienceKnowledge Discovery and Data Mining
- 27 June 2020
The GPT-GNN framework to initialize GNNs by generative pre-training introduces a self-supervised attributed graph generation task to pre-train a GNN so that it can capture the structural and semantic properties of the graph.
Microsoft Academic Graph: When experts are not enough
- Kuansan Wang, Zhihong Shen, Chiyuan Huang, Chieh-Han Wu, Yuxiao Dong, Anshul Kanakia
- Computer ScienceQuantitative Science Studies
- 23 January 2020
The design, schema, and technical and business motivations behind MAG are described and how MAG can be used in analytics, search, and recommendation scenarios are elaborated.
ERD'14: entity recognition and disambiguation challenge
- David Carmel, Ming-Wei Chang, E. Gabrilovich, B. Hsu, Kuansan Wang
- Computer ScienceAnnual International ACM SIGIR Conference on…
- 3 July 2014
It is shown how the pooling technique is adapted to address the difficulties of gathering annotations for the entity linking task, and how the task definition, issues encountered during annotation, and detailed analysis of all the participating systems are provided.
DeepInf: Social Influence Prediction with Deep Learning
- J. Qiu, Jian Tang, Hao Ma, Yuxiao Dong, Kuansan Wang, Jie Tang
- Computer ScienceKnowledge Discovery and Data Mining
- 15 July 2018
Inspired by the recent success of deep neural networks in a wide range of computing applications, an end-to-end framework to learn users' latent feature representation for predicting social influence is designed, suggesting the effectiveness of representation learning for social applications.
Clickage: towards bridging semantic and intent gaps via mining click logs of search engines
- Xiansheng Hua, Linjun Yang, Jin Li
- Computer ScienceACM Multimedia
- 21 October 2013
It is argued that the massive amount of click data from commercial search engines provides a data set that is unique in the bridging of the semantic and intent gap, and preliminary studies on the power of large-scale click data are presented.
...
...