About Me I am a Senior Research Scientist/Software Engineer at Facebook, with rich experience building ads machine learning products and systems. At Facebook we work on large-scale ads ranking and delivery systems to make every user impression valuable. This is achieved by pushing the boundary of machine learning techniques and building advertiser centric products. Prior to that, I was in Facebook Marketplace to build large scale personalized ranking system and commerce platform to drive the growth of Marketplace Tab, BSG, and other channels. Research Interests Large-Scale Recommendation System and Ranking, Deep Neural Network, Representation Learning, Information Retrieval, Data Mining, Data Privacy
Publications 15. Vachik Dave, Baichuan Zhang, Pin-Yu Chen, Mohammad Al Hasan: Neural-Brane: An Inductive Approach for Attributed Network Embedding, ASONAM 2019
14. Vachik Dave, Baichuan Zhang, Pin-Yu Chen, Mohammad Al Hasan: Neural-Brane: Neural Bayesian Personalized Ranking for Attributed Network Embedding, Data Science and Engineering Journal 2019 13. Baichuan Zhang, Murat Dundar, Vachik Dave, Mohammad Al Hasan: Dirichlet Process Gaussian Mixture for Active Online Name Disambiguation by Particle Filter, in ACM JCDL 2019 12. Vachik Dave, Baichuan Zhang, Mohammad Al Hasan, Khalifeh Al Jadda, Mohammed Korayem: A combined representation learning approach for better job and skill recommendation, in CIKM 2018 11. Vachik Dave, Mohammad Al Hasan, Baichuan Zhang, Chandan Reddy: Predicting Interval Time for Reciprocal Link Creation using Survival Analysis, in Social Network Analysis and Mining, 2018. 10. Pin-Yu Chen, Baichuan Zhang, and Mohammad Al Hasan: Incremental Eigenpair Computation for Graph Laplacian Matrices: Theory and Applications, in Social Network Analysis and Mining, 2017, PDF 9. Baichuan Zhang, and Mohammad Al Hasan: Name Disambiguation in Anonymized Graphs using Network Embedding, in CIKM 2017 Proceedings of the 26th ACM International Conference on Information and Knowledge Management, Singapore. Research Track Full Paper. PDF 8. Baichuan Zhang, Noman Mohammed, Vachik Dave, and Mohammad Al Hasan: Feature Selection for Classification under Anonymity Constraint, in Transactions on Data Privacy, 2017, PDF 7. Baichuan Zhang, Murat Dundar, and Mohammad Al Hasan: Bayesian Non-Exhaustive Classification A Case Study: Online Name Disambiguation using Temporal Record Streams, in CIKM 2016 Proceedings of the 25th ACM International Conference on Information and Knowledge Management, Indianapolis, IN. Research Track Full Paper. PDF 6. Sutanay Choudhury, Khushbu Agarwal, Sumit Purohit, Baichuan Zhang, Meg Pirrung, Will Smith, and Mathew Thomas: NOUS: Construction and Querying of Dynamic Knowledge Graphs, IEEE International Conference on Data Engineering (ICDE) 2017, PDF 5. Pin-Yu Chen, Baichuan Zhang, Mohammad Al Hasan, and Alfred Hero: Incremental Method for Spectral Clustering of Increasing Orders, in KDD Workshop on Mining and Learning with Graphs (MLG 2016), San Francisco, CA. PDF 4. Baichuan Zhang, Sutanay Choudhury, Mohammad Al Hasan, Xia Ning, Khushbu Agarwal, Sumit Purohit, and Paola Pesntez Cabrera: Trust from the past: Bayesian Personalized Ranking based Link Prediction in Knowledge Graphs, in SDM Workshop on Mining Networks and Graphs (MNG 2016), Miami, FL. PDF 3. Murat Dundar, Qiang Kou, Baichuan Zhang, Yicheng He, and Bartek Rajwa: Simplicity of Kmeans versus Deepness of Deep Learning: A Case of Unsupervised Feature Learning with Limited Data, in IEEE International Conference on Machine Learning Applications, 2015, Miami, FL. PDF 2. Baichuan Zhang, Tanay Kumar Saha, and Mohammad Al Hasan: Name Disambiguation from link data in a collaboration graph using temporal and topological features, in Social Network Analysis and Mining, 2015, PDF 1. Baichuan Zhang, Tanay Kumar Saha, and Mohammad Al Hasan: Name Disambiguation from link data in a collaboration graph, in 2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM Beijing, China. PDF Industrial Experience
Professional Service
Contact
|