no code implementations • 21 Aug 2023 • M. Maruf, Arka Daw, Amartya Dutta, Jie Bu, Anuj Karpatne
Furthermore, we propose random cropping as a stochastic aggregation technique that improves the performance of saliency, making it a strong alternative to CAM for WS3.
1 code implementation • 24 May 2023 • Jie Bu, Kazi Sajeed Mehrab, Anuj Karpatne
Conditional graph generation tasks involve training a model to generate a graph given a set of input conditions.
1 code implementation • 5 Jul 2022 • Arka Daw, Jie Bu, Sifan Wang, Paris Perdikaris, Anuj Karpatne
In this paper, we provide a novel perspective of failure modes of PINNs by hypothesizing that training PINNs relies on successful "propagation" of solution from initial and/or boundary condition points to interior points.
1 code implementation • NeurIPS 2021 • Jie Bu, Arka Daw, M. Maruf, Anuj Karpatne
We also theoretically show that the learning objective of DAM is directly related to minimizing the L0 norm of the masking layer.
1 code implementation • 20 Jan 2021 • Jie Bu, Anuj Karpatne
We propose quadratic residual networks (QRes) as a new type of parameter-efficient neural network architecture, by adding a quadratic residual term to the weighted sum of inputs before applying activation functions.
1 code implementation • 2 Sep 2020 • Jie Bu, M. Maruf, Arka Daw
In this paper, we proposed the \textit{link injection}, a novel method that helps any differentiable graph machine learning models to go beyond observed connections from the input data in an end-to-end learning fashion.
1 code implementation • 2 Jul 2020 • Mohannad Elhamod, Jie Bu, Christopher Singh, Matthew Redell, Abantika Ghosh, Viktor Podolskiy, Wei-Cheng Lee, Anuj Karpatne
Physics-guided Neural Networks (PGNNs) represent an emerging class of neural networks that are trained using physics-guided (PG) loss functions (capturing violations in network outputs with known physics), along with the supervision contained in data.
1 code implementation • 6 Nov 2019 • Nikhil Muralidhar, Jie Bu, Ze Cao, Long He, Naren Ramakrishnan, Danesh Tafti, Anuj Karpatne
In such situations, it is often useful to rely on machine learning methods to fill in the gap by learning a model of the complex physical process directly from simulation data.