Last updated on Jun 26, 2019. This page is still under construction.
Lab of Media and Network
Department of Computer Science and Technology
Beijing, China. 100084.
Email: majx13fromthu αt gmail dοt com
Jianxin Ma is pursuing a master’s degree in Computer Science and Technology at Tsinghua University, where he obtained a bachelor’s degree in Computer Science and Technology in 2017.
He conducts research under the supervision of Professor Wenwu Zhu and Peng Cui.
His research interests are mainly in machine learning, in particular representation learning, on relational data such as graphs, which has broad applications, ranging from social network analysis to recommender systems.
In particular, he strives to unify probabilistic generative modeling and deep representation learning, so as to accurately reveal the highly complex generating processes behind graph data and subsequently improve the robustness and interpretability of machine learning algorithms for graphs.
Jianxin Ma, Peng Cui, Kun Kuang, Xin Wang, Wenwu Zhu. Disentangled Graph Convolutional Networks. In Proceedings of the Thirty-Sixth International Conference on Machine Learning (ICML 2019). [code]
- Keywords: Graph neural networks. Disentangled representation learning. Capsule neural networks.
Ke Tu, Jianxin Ma, Peng Cui, Jian Pei, Wenwu Zhu. AutoNRL: Hyperparameter Optimization for Massive Network Representation Learning. In Proceedings of the Twenty-Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2019, Research Track). [code]
- Keywords: AutoML. Meta learning. Machine learning on graphs. Bayesian optimization.
Jianxin Ma, Peng Cui, Xiao Wang, Wenwu Zhu. Hierarchical Taxonomy Aware Network Embedding. In Proceedings of the Twenty-Forth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2018, Research Track). [code]
- Keywords: Nested Chinese restaurant processes. Expectation-Maximization (EM). Hierarchical clustering.
Jianxin Ma, Peng Cui, Wenwu Zhu. DepthLGP: Learning Embeddings of Out-of-Sample Nodes in Dynamic Networks. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018). [code][supp]
- Keywords: Gaussian processes. Out-of-sample extension. Universal approximation theorem.