Huiyuan Chen

Huiyuan Chen

Auto-generated profile, based on publicly available information

Huiyuan Chen

Case Western Reserve University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 July 2020 in PLOS Computational Biology
Verified
Journal Article
Open access
PDF file
HCHuiyuan Chen
Huiyuan Chen
FCFeixiong Cheng
Feixiong Cheng
JLJing Li
Jing Li
Computational drug repositioning and drug-target prediction have become essential tasks in the early stage of drug discovery. In previous studies, these two tasks have often been considered separately. However, the entities studied in these two tasks (i.e., drugs, targets, and diseases) are inherently related. On one hand, drugs interact with targets in cells to modulate target activities, which in turn alter biological pathways to promote healthy functions and to treat diseases. On the other hand, both drug repositioning and drug-target prediction involve the same drug feature space, which naturally connects these two problems and the two domains (diseases and targets). By using the wisdom of the crowds, it is possible to transfer knowledge from one of the domains to the other. The existence of relationships among drug-target-disease motivates us to jointly consider drug repositioning and drug-target prediction in drug discovery. In this paper, we present a novel approach called iDrug, which seamlessly integrates drug repositioning and drug-target prediction into one coherent model via cross-network embedding. In particular, we provide a principled way to transfer knowledge from these two domains and to enhance prediction performance for both tasks. Using real-world datasets, we demonstrate that iDrug achieves superior performance on both learning tasks compared to several state-of-the-art approaches. Our code and datasets are available at: https://github.com/Case-esaC/iDrug. Traditional high-throughput techniques for drug discovery are often expensive, time-consuming, and with high failure rates. Computational drug repositioning and drug-target prediction have thus become essential tasks in the early stage drug discovery. The emergence of large-scale heterogeneous biological networks has offered unprecedented opportunities for developing machine learning approaches to identify novel drug-disease or drug-target interactions. However, most existing works focused either on the drug-disease network or on the drug-target network, thus failed to capture the inherent dependencies between these two networks. These two biological networks are naturally connected since they involve the same drug feature space. In our opinion, ignoring this rich source of information is a major shortcoming of some existing works. In this paper, we present a novel approach called iDrug, which seamlessly integrates the drug-disease network and the drug-target network into one coherent model via cross-network embedding. As a result, iDrug is able to take full usage of the knowledge within these two biological networks to better exploit new biomedical insights of drug-target-disease. Therefore, iDrug has broad applications in drug discovery.

4 August 2023
Verified
Conference Paper
Open access
ZXZhe Xu
Zhe Xu
YCYuzhong Chen
Yuzhong Chen
MPMenghai Pan
Menghai Pan
HCHuiyuan Chen
Huiyuan Chen
MDMahashweta Das
Mahashweta Das
HTHanghang Tong
Hanghang Tong
The huge volume of emerging graph datasets has become a double-bladed sword for graph machine learning. On the one hand, it empowers the success of a myriad of graph neural networks (GNNs) with strong empirical performance. On the other hand, training modern graph neural networks on huge graph data is computationally expensive. How to distill the given graph dataset while retaining most of the trained models' performance is a challenging problem. Existing efforts try to approach this problem by solving meta-learning-based bilevel optimization objectives. A major hurdle lies in that the exact solutions of these methods are computationally intensive and thus, most, if not all, of them are solved by approximate strategies which in turn hurt the distillation performance. In this paper, inspired by the recent advances in neural network kernel methods, we adopt a kernel ridge regression-based meta-learning objective which has a feasible exact solution. However, the computation of graph neural tangent kernel is very expensive, especially in the context of dataset distillation. As a response, we design a graph kernel, named LiteGNTK, tailored for the dataset distillation problem which is closely related to the classic random walk graph kernel. An effective model named Kernel rıdge regression-based graph Dataset Distillation (KIDD) and its variants are proposed. KIDD shows nice efficiency in both the forward and backward propagation processes. At the same time, KIDD shows strong empirical performance over 7 real-world datasets compared with the state-of-the-art distillation methods. Thanks to the ability to find the exact solution of the distillation objective, the learned training graphs by KIDD can sometimes even outperform the original whole training set with as few as 1.65% training graphs.

4 August 2023
Verified
Conference Paper
Open access
SWSong Wang
Song Wang
XFXingbo Fu
Xingbo Fu
KDKaize Ding
Kaize Ding
CCChen Chen
Chen Chen
HCHuiyuan Chen
Huiyuan Chen
JLJundong Li
Jundong Li

21 October 2023
Verified
Conference Paper
Open access
CYChin-Chia Michael Yeh
Chin-Chia Michael Yeh
XDXin Dai
Xin Dai
HCHuiyuan Chen
Huiyuan Chen
YZYan Zheng
Yan Zheng
YFYujie Fan
Yujie Fan
WZWei Zhang
Wei Zhang
A foundation model is a machine learning model trained on a large and diverse set of data, typically using self-supervised learning-based pre-training techniques, that can be adapted to various downstream tasks. However, current research on time series pre-training has predominantly focused on models trained exclusively on data from a single domain. As a result, these models possess domain-specific knowledge that may not be easily transferable to time series from other domains. In this paper, we aim to develop an effective time series foundation model by leveraging unlabeled samples from multiple domains. To achieve this, we repurposed the publicly available UCR Archive and evaluated four existing self-supervised learning-based pre-training methods, along with a novel method, on the datasets. We tested these methods using four popular neural network architectures for time series to understand how the pre-training methods interact with different network designs. Our experimental results show that pre-training improves downstream classification tasks by enhancing the convergence of the fine-tuning process. Furthermore, we found that the proposed pre-training method, when combined with the Transformer, outperforms the alternatives. The proposed method outperforms or achieves equal performance compared to the second best method in ~93% of downstream tasks.

20 August 2017
Verified
Conference Paper
Open access
PDF file
HCHuiyuan Chen
Huiyuan Chen
JLJing Li
Jing Li
Drug repositioning is a promising strategy in drug discovery. New biomedical insights of drug-target-disease relationships are important in drug repositioning, and such relationships have been intensively studied recently. Most of the studies utilize network-based computational approaches based on drug and disease similarities. However, one common limitation of existing approaches is that both drug similarities and disease similarities are defined based on a single feature of drugs/diseases. In reality, the relationships between drug (or disease) pairs can be characterized based on many different features. Therefore, it is increasingly important to include them in drug repositioning studies. In this study, we propose a flexible and robust multi-source learning (FRMSL) framework to integrate multiple heterogeneous data sources for drug-disease association predictions. We first construct a two-layer heterogeneous network consisting of drug nodes, disease nodes and known drug-disease relationships. The drug repositioning problem can thus be treated as a missing link prediction problem on the heterogeneous graph and can be solved using Kronecker regularized least square (KronRLS) method. Multiple data sources describing drugs and diseases are incorporated into the framework using similarity-based kernels. In practice, a great challenge in such data integration projects is the data incompleteness problem due to the nature of data generation and collection. To address this issue, we develop a novel multi-view learning algorithm based on symmetric nonnegative matrix factorization (SymNMF). Extensive experimental studies show that our framework outperforms several recent network-based methods.

4 March 2024
Verified
Conference Paper
Open access
HCHuiyuan Chen
Huiyuan Chen
VLVivian Lai
Vivian Lai
HJHongye Jin
Hongye Jin
ZJZhimeng Jiang
Zhimeng Jiang
MDMahashweta Das
Mahashweta Das
XHXia Hu
Xia Hu
Contrastive Learning (CL) has shown promising performance in collaborative filtering. The key idea is to use contrastive loss to generate augmentation-invariant embeddings by maximizing the Mutual Information between different augmented views of the same instance. However, we empirically observe that existing CL models suffer from the dimensional collapse issue, where user/item embeddings only span a low-dimension subspace of the entire feature space. This suppresses other dimensional information and weakens the distinguishability of embeddings. Here we propose a non-contrastive learning objective, named nCL, which explicitly mitigates dimensional collapse of representations in collaborative filtering. Our nCL aims to achieve geometric properties of Alignment and Compactness on the embedding space. In particular, the alignment tries to push together representations of positive-related user-item pairs, while compactness tends to find the optimal coding length of user/item embeddings, subject to a given distortion. More importantly, our nCL does not require data augmentation nor negative sampling during training, making it scalable to large datasets compared to contrastive learning methods. Experimental results demonstrate the superiority of our nCL.