Last updated on May 31, 2021.
Email1: majx13fromthu αt gmail dοt com
Email2: jason.mjx αt alibaba-inc dοt com
Jianxin Ma is now doing applied research at Alibaba Group.
He received his master’s degree in Computer Science and Technology in 2020 June at Tsinghua University, where he also obtained his bachelor’s degree in Computer Science and Technology in 2017.
During his graduate studies, he conducted research under the supervision of Professor Wenwu Zhu and Peng Cui.
His research interests are mainly in machine learning, in particular representation learning, of relational data such as graphs and of sequential data such as texts and user behavior sequences, which has broad applications in search, recommendations and advertising.
Selected Publications (See Google Scholar for Full Publications)
Chang Zhou*, Jianxin Ma*, Jianwei Zhang, Jingren Zhou, Hongxia Yang. Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems. In Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2021, ADS Track).
- Keywords: Contrastive learning. Bias reduction. Inverse propensity weighting. Recommender systems.
Jianxin Ma, Chang Zhou, Hongxia Yang, Peng Cui, Xin Wang, Wenwu Zhu. Disentangled Self-Supervision in Sequential Recommenders. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2020, Research Track).
- Keywords: Self-supervised learning. Contrastive learning. Disentanglement. Recommender systems.
Jianxin Ma*, Chang Zhou*, Peng Cui, Hongxia Yang, Wenwu Zhu. Learning Disentangled Representations for Recommendation. In Proceedings of the Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019). [poster] [code & dataset]
- Keywords: Relational data. Disentangled representation learning. Recommender systems. User behavior.
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 25th 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. Real-time. Cold start.
2020.07-Present. Alibaba Group. Full Time.
2019.04-2020.6. Alibaba Group. Research Intern.
2018.07-2018.10. WeChat, Tencent. Research Intern.