no code implementations • 26 Oct 2023 • Guangliang Liu, Zhiyu Xue, Xitong Zhang, Kristen Marie Johnson, Rongrong Wang
Fine-tuning pretrained language models (PLMs) for downstream tasks is a large-scale optimization problem, in which the choice of the training algorithm critically determines how well the trained model can generalize to unseen test data, especially in the context of few-shot learning.
no code implementations • 3 Jun 2023 • Zhichao Hou, Xitong Zhang, Wei Wang, Charu C. Aggarwal, Xiaorui Liu
This work presents the first investigation into the robustness of GNNs in the context of directed graphs, aiming to harness the profound trust implications offered by directed graphs to bolster the robustness and resilience of GNNs.
no code implementations • 30 May 2023 • Xitong Zhang, Avrajit Ghosh, Guangliang Liu, Rongrong Wang
It is widely recognized that the generalization ability of neural networks can be greatly enhanced through carefully designing the training procedure.
no code implementations • 2 Feb 2023 • Avrajit Ghosh, He Lyu, Xitong Zhang, Rongrong Wang
It is well known that the finite step-size ($h$) in Gradient Descent (GD) implicitly regularizes solutions to flatter minima.
no code implementations • 8 Dec 2022 • Yanhua Liu, Xitong Zhang, Ilya Tsvankin, Youzuo Lin
The method remains robust even if the testing data are distorted due to problems in the field data acquisition.
1 code implementation • 22 Feb 2022 • Yixuan He, Xitong Zhang, JunJie Huang, Benedek Rozemberczki, Mihai Cucuringu, Gesine Reinert
While many networks are signed or directed, or both, there is a lack of unified software packages on graph neural networks (GNNs) specially designed for signed and directed networks.
no code implementations • 3 Feb 2022 • Shihang Feng, Peng Jin, Xitong Zhang, Yinpeng Chen, David Alumbaugh, Michael Commer, Youzuo Lin
We explore a multi-physics inversion problem from two distinct measurements~(seismic and EM data) to three geophysical properties~(velocity, conductivity, and CO$_2$ saturation).
2 code implementations • 4 Nov 2021 • Chengyuan Deng, Shihang Feng, Hanchen Wang, Xitong Zhang, Peng Jin, Yinan Feng, Qili Zeng, Yinpeng Chen, Youzuo Lin
The recent success of data-driven FWI methods results in a rapidly increasing demand for open datasets to serve the geophysics community.
no code implementations • ICLR 2022 • Peng Jin, Xitong Zhang, Yinpeng Chen, Sharon Xiaolei Huang, Zicheng Liu, Youzuo Lin
In particular, we use finite difference to approximate the forward modeling of PDE as a differentiable operator (from velocity map to seismic data) and model its inversion by CNN (from seismic data to velocity map).
no code implementations • 22 Jun 2021 • Yuxin Yang, Xitong Zhang, Qiang Guan, Youzuo Lin
To validate the effectiveness of our data augmentation techniques, we apply them to solve a subsurface seismic full-waveform inversion using simulated CO$_2$ leakage data.
no code implementations • 25 May 2021 • Shihang Feng, Xitong Zhang, Brendt Wohlberg, Neill Symons, Youzuo Lin
Via both numerical and expert evaluation, we conclude that our models can produce high-quality 2D/3D seismic imaging data at a reasonable cost, offering the possibility of real-time monitoring or even near-future forecasting of the CO$_2$ storage reservoir.
1 code implementation • NeurIPS 2021 • Xitong Zhang, Yixuan He, Nathan Brugnone, Michael Perlmutter, Matthew Hirn
In this paper, we propose MagNet, a spectral GNN for directed graphs based on a complex Hermitian matrix known as the magnetic Laplacian.