About Le Song
Professor Le Song is the Department Chair and Professor in the Machine Learning Department at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI).
Prof. Le Song was an Associate Professor of Computational Science and Engineering and also the Associate Director of Center for Machine Learning at Georgia Institute of Technology in the USA. He holds the PhD in Computer Science from the University of Sydney and National ICT Australia. He taught in different educational institutions in the USA.
Prof. Le Song published more than 160 papers in peer-reviewed top machine learning conferences and journals such as NeurIPS, ICML, ICLR, AISTATS and JMLR over the past 15 years. He was invited as an Area Chair in many international conferences. Prof. Le Song is also an active member of several regional and international groups in the field of Machine Learning, Artificial Intelligence and Statistics, such as the board member of the International Conference on Machine Learning.
Prof. Le Song is an experienced educator and researcher in the field of Machine Learning and Artificial Intelligence. He received honors and awards for his research and articles as a Principal Investigator and co-Principal Investigator.
Prof. Le Song’s impressive portfolio includes his several years’ experience in various Institutes such as Georgia Institute of Technology, Google Research, Carnegie Mellon University and National ICT Australia, he developed machine learning methods and algorithms for complex and dynamic data, machine learning and cross-campus multi-disciplinary research, large scale machine learning package for Internet data, nonparametric probabilistic graphical models for complex social and biological data and analyzed sensor time series data using kernel methods.
Prof. Le Song’s remarkable works won several best paper awards at the ACM Conference on Recommendation System (Recsys) in 2016, Artificial Intelligence and Statistics (AISTATS) in 2016, IEEE International Parallel & Distributed Processing Symposium (IPDPS) in 2015, Neural Information Processing Systems (NeurIPS) in 2013, and International Conference on Machine Learning (ICML) in 2010. He was also the recipient of the National Science Foundation CAREER Award in 2014, and Outstanding Junior Faculty Research Award in 2014 and Lockheed Martin Inspirational Young Faculty Award in 2014.
|Present||Department Chair and Professor, Mohamed bin Zayed University of Artificial Intelligence ‐ Department of Machine Learning|
Honors and Awards
- ACM Conference on Recommendation System (Recsys)’ 2016 Best Paper Award
- Artificial Intelligence and Statistics (AISTATS)’ 2016 Best Paper Award
- IEEE International Parallel & Distributed Processing Symposium (IPDPS)’ 2015 Best Paper Award
- Neural Information Processing Systems (NeurIPS)’ 2013 Best Paper Award
- International Conference on Machine Learning (ICML)’ 2010 Best Paper Award
- National Science Foundation CAREER Award in 2014
- Outstanding Junior Faculty Research Award in 2014
- Lockheed Martin Inspirational Young Faculty Award in 2014.
Journal Articles (1)
Guest Editorial: Non-Euclidean Machine Learning IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)
Over the past decade, deep learning has had a revolutionary impact on a broad range of fields such as computer vision and image processing, computational photography, medical imaging and speech and language analysis and synthesis ...
Conference Proceedings (4)
Concentric Spherical Neural Network for 3D Representation Learning Proceedings of the International Joint Conference on Neural Networks (2022)
Learning 3D representations of point clouds that generalize well to arbitrary orientations is a challenge of practical importance in domains ranging from computer vision to molecular modeling. The proposed approach uses a concentric spherical spatial ...
ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 (2022)
We study the problem of extracting N-ary relation tuples from scientific articles. This task is challenging because the target knowledge tuples can reside in multiple parts and modalities of the document. Our proposed method RESEL ...
Locality Sensitive Teaching Advances in Neural Information Processing Systems (2021)
The emergence of the Internet-of-Things (IoT) sheds light on applying the machine teaching (MT) algorithms for online personalized education on home devices. This direction becomes more promising during the COVID-19 pandemic when in-person education becomes ...
BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference (2021)
We study the problem of learning a named entity recognition (NER) tagger using noisy labels from multiple weak supervision sources. Though cheap to obtain, the labels from weak supervision sources are often incomplete, inaccurate, and ...
Proto: Program-Guided Transformer for Program-Guided Tasks arXiv (2022)
Programs, consisting of semantic and structural information, play an important role in the communication between humans and agents. Towards learning general program executors to unify perception, reasoning, and decision making, we formulate program-guided tasks which ...
PRBOOST: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning arXiv (2022)
Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set is tedious and difficult. We study interactive weakly-supervised learning-the problem of ...
Molecule Generation for Drug Design: A Graph Learning Perspective arXiv (2022)
Machine learning has revolutionized many fields, and graph learning is recently receiving increasing attention. From the application perspective, one of the emerging and attractive areas is aiding the design and discovery of molecules, especially in ...
Learning Temporal Rules from Noisy Timeseries Data arXiv (2022)
Events across a timeline are a common data representation, seen in different temporal modalities. Individual atomic events can occur in a certain temporal ordering to compose higher level composite events. Examples of a composite event ...
Molecular Attributes Transfer from Non-Parallel Data arXiv (2021)
Optimizing chemical molecules for desired properties lies at the core of drug development. Despite initial successes made by deep generative models and reinforcement learning methods, these methods were mostly limited by the requirement of predefined ...
A Biased Graph Neural Network Sampler with Near-Optimal Regret arXiv (2021)
Graph neural networks (GNN) have recently emerged as a vehicle for applying deep network architectures to graph and relational data. However, given the increasing size of industrial datasets, in many practical situations the message passing ...
Multi-Task Learning of Order-Consistent Causal Graphs arXiv (2021)
We consider the problem of discovering K related Gaussian directed acyclic graphs (DAGs), where the involved graph structures share a consistent causal order and sparse unions of supports. Under the multi-task learning setting, we propose ...
Roma: Robust Model Adaptation for Offline Model-Based Optimization arXiv (2021)
We consider the problem of searching an input maximizing a black-box objective function given a static dataset of input-output queries. A popular approach to solving this problem is maintaining a proxy model, e.g., a deep ...