Search Results for author: Chengyuan Deng

Found 9 papers, 2 papers with code

Impossibility of Depth Reduction in Explainable Clustering

no code implementations4 May 2023 Chengyuan Deng, Surya Teja Gavva, Karthik C. S., Parth Patel, Adarsh Srinivasan

Formally, we show that there exists a data set X in the Euclidean plane, for which there is a decision tree of depth k-1 whose k-means/k-median cost matches the optimal clustering cost of X, but every decision tree of depth less than k-1 has unbounded cost w. r. t.


On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversion

no code implementations28 Nov 2021 Chengyuan Deng, Youzuo Lin

For robustness, we prove the upper bounds of the deviation between the predictions from clean and noisy data.

Image-to-Image Translation Translation

OpenFWI: Large-Scale Multi-Structural Benchmark Datasets for Seismic Full Waveform Inversion

2 code implementations4 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.

2k Benchmarking +2

On the Global Self-attention Mechanism for Graph Convolutional Networks

no code implementations21 Oct 2020 Chen Wang, Chengyuan Deng

Applying Global Self-attention (GSA) mechanism over features has achieved remarkable success on Convolutional Neural Networks (CNNs).

SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations

no code implementations27 Nov 2019 Chen Wang, Chengyuan Deng, Vladimir Ivanov

Variational Autoencoders (VAEs) are powerful in data representation inference, but it cannot learn relations between features with its vanilla form and common variations.

Image Reconstruction Inductive Bias +1

Adaptive Ensemble of Classifiers with Regularization for Imbalanced Data Classification

no code implementations9 Aug 2019 Chen Wang, Chengyuan Deng, Zhoulu Yu, Dafeng Hui, Xiaofeng Gong, Ruisen Luo

In addition, the proposed method has other preferred properties such as special advantages in dealing with highly imbalanced data, and it pioneers the research on the regularization for dynamic ensemble methods.

Classification General Classification

Imbalance-XGBoost: Leveraging Weighted and Focal Losses for Binary Label-Imbalanced Classification with XGBoost

1 code implementation5 Aug 2019 Chen Wang, Chengyuan Deng, Suzhen Wang

The paper presents Imbalance-XGBoost, a Python package that combines the powerful XGBoost software with weighted and focal losses to tackle binary label-imbalanced classification tasks.

Binary Classification Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.