News

  • 06/09, 2019. Gave a talk on group reading meeting about Connection between GAN, IRL and EBM. 
  • 25/10, 2019. Gave a talk about Information Theory towards the first-year undergraduates in Yuanpei College, Peking University, invited by Prof. Hongzhe Wang.
gan_irl.pdf
File Size: 585 kb
File Type: pdf
Download File
infomation_theory.pdf
File Size: 1193 kb
File Type: pdf
Download File

Selected Publications

​Cognitive Graph for Multi-Hop Reading Comprehension at Scale
Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, Jie Tang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL'19)
Abstract:
We propose a new CogQA framework for multi-hop question answering in web-scale documents. Inspired by the dual process theory in cognitive science, the framework gradually builds a\textit {cognitive graph} in an iterative process by coordinating an implicit extraction module (System 1) and an explicit reasoning module (System 2). While giving accurate answers, our framework further provides explainable reasoning paths. Specifically, our implementation based on BERT and graph neural network efficiently handles millions of documents for multi-hop reasoning questions in the HotpotQA fullwiki dataset, achieving a winning joint F1 score of 34.9 on the leaderboard, compared to 23.6 of the best competitor.
Links: [pdf]  [code]
Semi-supervised Learning on Graphs with Generative Adversarial Nets
Ming Ding, Jie Tang, Jie Zhang
Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM'18)
Abstract:
We investigate how generative adversarial nets (GANs) can help semi-supervised learning on graphs. We first provide insights on working principles of adversarial learning over graphs and then present GraphSGAN, a novel approach to semi-supervised learning on graphs. In GraphSGAN, generator and classifier networks play a novel competitive game. At equilibrium, generator generates fake samples in low-density areas between subgraphs. In order to discriminate fake samples from the real, classifier implicitly takes the density property of subgraph into consideration. An efficient adversarial learning algorithm has been developed to improve traditional normalized graph Laplacian regularization with a theoretical guarantee. Experimental results on several different genres of datasets show that the proposed GraphSGAN significantly outperforms several state-of-the-art methods. GraphSGAN can be also trained using mini-batch, thus enjoys the scalability advantage.
Links: [pdf] [code]
Towards Knowledge-Based Recommender Dialog System
Qibin Chen, Junyang Lin, Yichang Zhang, Ming Ding, Yukuo Cen, Hongxia Yang, Jie Tang
2019 Conference on Empirical Methods in Natural Language Processing (EMNLP'19) 
​Abstract:
In this paper, we propose a novel end-to-end framework called KBRD, which stands for Knowledge-Based Recommender Dialog System. It integrates the recommender system and the dialog generation system. The dialog system can enhance the performance of the recommendation system by introducing knowledge-grounded information about users’ preferences, and the recommender system can improve that of the dialog generation system by providing recommendation-aware vocabulary bias. Experimental results demonstrate that our proposed model has significant advantages over the baselines in both the evaluation of dialog generation and recommendation. A series of analyses show that the two systems can bring mutual benefits to each other, and the introduced knowledge contributes to both their performances.
Links: [pdf] [code]
ProNE: Fast and Scalable Network Representation Learning
Jie Zhang, Yuxiao Dong, Yan Wang, Jie Tang, Ming Ding
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI'19)
Abstract:
Recent advances in network embedding has revolutionized the field of graph and network mining. However, (pre-)training embeddings for very large-scale networks is computationally challenging for most existing methods. In this work, we present ProNE---a fast, scalable, and effective model, whose single-thread version is 10--400x faster than efficient network embedding benchmarks with 20 threads, including LINE, DeepWalk, node2vec, GraRep, and HOPE. As a concrete example, the single-version ProNE requires only 29 hours to embed a network of
hundreds of millions of nodes while it takes LINE weeks and DeepWalk months by using 20 threads. To achieve this, ProNE first initializes network embeddings efficiently by formulating the task as sparse matrix factorization. The second step of ProNE is to enhance the embeddings by propagating them in the spectrally modulated space. Extensive experiments on networks of various scales and types demonstrate that ProNE achieves both effectiveness and significant efficiency superiority when compared to the aforementioned baselines. In addition, ProNE's embedding enhancement step can be also generalized for improving other models at speed, e.g., offering >10% relative gains for the used baselines. 
Links: [pdf] [code]

Awards

  • Outstanding Undergraduate Thesis of Tsinghua, 2018
  • Outstanding Graduate of Tsinghua University, 2018
  • Outstanding student cadre in Tsinghua University, 2017.
  • CCSP (CCF Collegiate Computer Systems and Programming Contest), Golden Medal (6th / 343 selected participants), 2016
  • Tsinghua University Academic Excellence Award, 2015
  • NOI (National Olympiad in Informatics), Bronze Medal, 2013

More about me

  • I was once the president of Students’ Association of Calligraphy in Tsinghua University, in charge of organizing teaching activities for schoolmates. However, the CS major seems harmful to my hobby because now I typing instead of writing everyday TAT
  • I was the vice president of Students’ Association of Science and Technology. Project Arena9 launched by me and other fellow members has become a mature platform for Game AI contests.
  • I was the teaching assistant of Data Structure Course (instructed by Junhui Deng) in Tsinghua University, which was voted as top 10 best courses that year.
  • My favorite sport is basketball and my favorite star is Russell Westbrook!
  • I am looking for a long-term academic partner, who is skilled at applied math OR cognitive science. Please contact me if you want collaborations.