activity
20172022
most citedBridging Mode Connectivity in Loss Landscapes and Adversarial Robustness

33 citations · 134 across the 22 of their papers we have counts for

collaborators
Showing cs.LGShow all

19 papers · 1 filter

cs.LG2022

Reducing Down(stream)time: Pretraining Molecular GNNs using Heterogeneous AI Accelerators

Jenna A. Bilbrey, Kristina M. Herman, Henry Sprueill +6

The demonstrated success of transfer learning has popularized approaches that involve pretraining models from massive data sources and subsequent finetuning towards a specific task…

cs.LG20221 cited

Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions

Chanakya Ekbote, Moksh Jain, Payel Das +1

Generative Flow Networks (GFlowNets) have demonstrated significant performance improvements for generating diverse discrete objects given a reward function , indicating t…

cs.LG20221 cited

SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data

Ching-Yun Ko, Pin-Yu Chen, Jeet Mohapatra +2

Recent success in fine-tuning large models, that are pretrained on broad data at scale, on downstream tasks has led to a significant paradigm shift in deep learning, from task-cent…

cs.LG2022

Learning Geometrically Disentangled Representations of Protein Folding Simulations

N. Joseph Tatro, Payel Das, Pin-Yu Chen +2

Massive molecular simulations of drug-target proteins have been used as a tool to understand disease mechanism and develop therapeutics. This work focuses on learning a generative…

cs.LG202218 cited

Data-Efficient Graph Grammar Learning for Molecular Generation

Minghao Guo, Veronika Thost, Beichen Li +3

The problem of molecular generation has received significant attention recently. Existing methods are typically based on deep neural networks and require training on large datasets…

cs.LG2022

Fourier Representations for Black-Box Optimization over Categorical Variables

Hamid Dadkhahi, Jesus Rios, Karthikeyan Shanmugam +1

Optimization of real-world black-box functions defined over purely categorical variables is an active area of research. In particular, optimization and design of biological sequenc…