Learning from Interconnected Data
We focus on developing machine learning techniques that leverage interdependency structures in complex relational domains including social, information, and physical networks.
Funded Projects
- Robust Real-time Resource Forecasting for Pricing Scheme Design – Adobe 2022
- Time-series Prediction for Cloud Demand Forecasting – Adobe 2020
Publications
- Role-based graph embeddings – IICDE-TKDE 2023
- Role-based graph embeddings – IEEE Transactions on Knowledge and Data Engineering (TKDE) 2022
- Method and system for similarity-based multi-label learning – Patent Published 2020
- Ensemble Learning for Relational Data – Journal of Machine Learning Research 2020
- role2vec: Role-based network embeddings – KDD Deep Learning on Graphs (DLG) 2019
- Relational similarity machines (RSM): A similarity-based learning framework for graphs – IEEE Big Data 2018
- Interactive visual graph mining and learning – ACM Transactions on Intelligent Systems and Technology (TIST) 2018
- Similarity-based Multi-label Learning – International Joint Conference on Neural Networks (IJCNN) 2018
- Representation learning in large attributed graphs – WiML NIPS 2017
- Provenance Segmentation – TaPP 2016
- An analysis of how ensembles of collective classifiers improve predictions in graphs – ACM Conference on Information and Knowledge Management (CIKM) 2012
- Ensemble classification techniques for relational domains – PhD Thesis 2012
- Across-model collective ensemble classification – AAAI Conference on Artificial Intelligence 2011
- Multi-network fusion for collective inference – Workshop on Mining and Learning on Graphs (MLG) 2010
- A resampling technique for relational data graphs – ACM SIGKDD Conference on Knowledge Discovery and Data Mining Social Network Analysis (SNA) workshop 2008