3 code implementations • 7 Feb 2024 • Md Shamim Hussain, Mohammed J. Zaki, Dharmashankar Subramanian
We also obtain SOTA results on QM9, MOLPCBA, and LIT-PCBA molecular property prediction benchmarks via transfer learning.
Ranked #1 on Drug Discovery on LIT-PCBA(KAT2A)
no code implementations • 1 Feb 2024 • Xiao Shou, Dharmashankar Subramanian, Debarun Bhattacharjya, Tian Gao, Kristin P. Bennet
Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate event streams, to the best of our knowledge.
no code implementations • 1 Feb 2024 • Weiqin Chen, James Onyejizu, Long Vu, Lan Hoang, Dharmashankar Subramanian, Koushik Kar, Sandipan Mishra, Santiago Paternain
In this paper, we propose, analyze and evaluate adaptive primal-dual (APD) methods for SRL, where two adaptive LRs are adjusted to the Lagrangian multipliers so as to optimize the policy in each iteration.
no code implementations • 8 Sep 2023 • Elita Lobo, Oktie Hassanzadeh, Nhan Pham, Nandana Mihindukulasooriya, Dharmashankar Subramanian, Horst Samulowitz
The resulting matching enables the use of an available or curated business glossary for retrieval and analysis without or before requesting access to the data contents.
no code implementations • 29 Jun 2023 • Weiqin Chen, Dharmashankar Subramanian, Santiago Paternain
Furthermore, we propose a Safe Primal-Dual algorithm that can leverage both SPGs to learn safe policies.
1 code implementation • 2 Jun 2023 • Md Shamim Hussain, Mohammed J. Zaki, Dharmashankar Subramanian
However, the dynamic (i. e., input-dependent) nature of these pathways makes it difficult to prune dense self-attention during training.
Ranked #12 on Graph Regression on PCQM4Mv2-LSC
no code implementations • 19 Feb 2023 • Daniel Karl I. Weidele, Shazia Afzal, Abel N. Valente, Cole Makuch, Owen Cornec, Long Vu, Dharmashankar Subramanian, Werner Geyer, Rahul Nair, Inge Vejsbjerg, Radu Marinescu, Paulito Palmes, Elizabeth M. Daly, Loraine Franke, Daniel Haehn
AutoDOViz seeks to lower the barrier of entry for data scientists in problem specification for reinforcement learning problems, leverage the benefits of AutoDO algorithms for RL pipeline search and finally, create visualizations and policy insights in order to facilitate the typical interactive nature when communicating problem formulation and solution proposals between DO experts and domain experts.
no code implementations • 2 Oct 2022 • Weiqin Chen, Dharmashankar Subramanian, Santiago Paternain
In particular, we consider the notion of probabilistic safety.
no code implementations • 11 Feb 2022 • Karan Samel, Zelin Zhao, Binghong Chen, Shuang Li, Dharmashankar Subramanian, Irfan Essa, Le Song
Events across a timeline are a common data representation, seen in different temporal modalities.
no code implementations • 29 Sep 2021 • Karan Samel, Zelin Zhao, Binghong Chen, Shuang Li, Dharmashankar Subramanian, Irfan Essa, Le Song
Events across a timeline are a common data representation, seen in different temporal modalities.
3 code implementations • 7 Aug 2021 • Md Shamim Hussain, Mohammed J. Zaki, Dharmashankar Subramanian
The resultant framework - which we call Edge-augmented Graph Transformer (EGT) - can directly accept, process and output structural information of arbitrary form, which is important for effective learning on graph-structured data.
Ranked #1 on Graph Regression on PCQM4Mv2-LSC
no code implementations • 21 Feb 2020 • Tian Gao, Dharmashankar Subramanian, Karthikeyan Shanmugam, Debarun Bhattacharjya, Nicholas Mattei
Event datasets are sequences of events of various types occurring irregularly over the time-line, and they are increasingly prevalent in numerous domains.
no code implementations • NeurIPS 2018 • Debarun Bhattacharjya, Dharmashankar Subramanian, Tian Gao
Event datasets include events that occur irregularly over the timeline and are prevalent in numerous domains.
no code implementations • NeurIPS 2014 • Marek Petrik, Dharmashankar Subramanian
We describe how to use robust Markov decision processes for value function approximation with state aggregation.
no code implementations • 26 Sep 2013 • Marek Petrik, Dharmashankar Subramanian, Janusz Marecki
We propose solution methods for previously-unsolved constrained MDPs in which actions can continuously modify the transition probabilities within some acceptable sets.