1 code implementation • 18 Apr 2024 • Jingmin Sun, Yuxuan Liu, Zecheng Zhang, Hayden Schaeffer
More importantly, we provide three extrapolation studies to demonstrate that PROSE-PDE can generalize physical features through the robust training of multiple operators and that the proposed model can extrapolate to predict PDE solutions whose models or data were unseen during the training.
no code implementations • 3 Apr 2024 • Zecheng Zhang
Through a systematic study of five numerical examples, we compare the accuracy and cost of training a single neural operator for each operator independently versus training a MOL model using our proposed method.
1 code implementation • 31 Mar 2024 • Weihua Hu, Yiwen Yuan, Zecheng Zhang, Akihiro Nitta, Kaidi Cao, Vid Kocijan, Jure Leskovec, Matthias Fey
We present PyTorch Frame, a PyTorch-based framework for deep learning over multi-modal tabular data.
Ranked #1 on Binary Classification on kickstarter
no code implementations • 23 Feb 2024 • Christian Moya, Amirhossein Mollaali, Zecheng Zhang, Lu Lu, Guang Lin
In this paper, we adopt conformal prediction, a distribution-free uncertainty quantification (UQ) framework, to obtain confidence prediction intervals with coverage guarantees for Deep Operator Network (DeepONet) regression.
no code implementations • 29 Oct 2023 • Zecheng Zhang, Christian Moya, Lu Lu, Guang Lin, Hayden Schaeffer
Neural operators have been applied in various scientific fields, such as solving parametric partial differential equations, dynamical systems with control, and inverse problems.
1 code implementation • 28 Sep 2023 • Yuxuan Liu, Zecheng Zhang, Hayden Schaeffer
Approximating nonlinear differential equations using a neural network provides a robust and efficient tool for various scientific computing tasks, including real-time predictions, inverse problems, optimal controls, and surrogate modeling.
1 code implementation • 16 Jul 2023 • Bowen Song, Soo Min Kwon, Zecheng Zhang, Xinyu Hu, Qing Qu, Liyue Shen
However, training diffusion models in the pixel space are both data-intensive and computationally demanding, which restricts their applicability as priors for high-dimensional real-world data such as medical images.
no code implementations • 3 Nov 2021 • Guang Lin, Christian Moya, Zecheng Zhang
To enable DeepONets training with noisy data, we propose using the Bayesian framework of replica-exchange Langevin diffusion.
1 code implementation • NAACL 2022 • Yuxin Xiao, Zecheng Zhang, Yuning Mao, Carl Yang, Jiawei Han
Consequently, it is more challenging to encode the key information sources--relevant contexts and entity types.
Ranked #1 on Relation Extraction on CDR
no code implementations • 24 Feb 2021 • Liu Liu, Tieyong Zeng, Zecheng Zhang
In our framework, the solution is approximated by a neural network that satisfies both the governing equation and other constraints.
Numerical Analysis Numerical Analysis
no code implementations • 17 Nov 2020 • Eric Chung, Yalchin Efendiev, Wing Tat Leung, Sai-Mang Pun, Zecheng Zhang
In this work, we propose a multi-agent actor-critic reinforcement learning (RL) algorithm to accelerate the multi-level Monte Carlo Markov Chain (MCMC) sampling algorithms.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 31 Aug 2020 • Boris Chetverushkin, Eric Chung, Yalchin Efendiev, Sai-Mang Pun, Zecheng Zhang
This multiscale problem is interesting from a multiscale methodology point of view as the model problem has a hyperbolic multiscale term, and designing multiscale methods for hyperbolic equations is challenging.
Numerical Analysis Numerical Analysis 65M22, 65M60
no code implementations • 13 Apr 2020 • Huajie Shao, Dachun Sun, Jiahao Wu, Zecheng Zhang, Aston Zhang, Shuochao Yao, Shengzhong Liu, Tianshi Wang, Chao Zhang, Tarek Abdelzaher
Motivated by this trend, we describe a novel item-item cross-platform recommender system, $\textit{paper2repo}$, that recommends relevant repositories on GitHub that match a given paper in an academic search system such as Microsoft Academic.
1 code implementation • 2019 IEEE International Conference on Big Data (Big Data) 2019 • Yuxin Xiao, Zecheng Zhang, Carl Yang, ChengXiang Zhai
In this way, it leverages both local and non-local information simultaneously.
Ranked #1 on Heterogeneous Node Classification on DBLP (PACT) 14k (Macro-F1 (60% training data) metric)