Dongyuan Tian

Dongyuan Tian

Auto-generated profile, based on publicly available information

Dongyuan Tian

Jilin University

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
14 August 2025 in Entropy
Verified
Journal Article
Open access
PDF file
TWTao Wang
Tao Wang
DTDongyuan Tian
Dongyuan Tian
HZHaonan Zhao
Haonan Zhao
JLJiamin Liu
Jiamin Liu
WWWeijie Wang
Weijie Wang
GLGuixia Liu
Guixia Liu
Retinal vessel segmentation plays a crucial role in diagnosing various retinal and cardiovascular diseases and serves as a foundation for computer-aided diagnostic systems. Blood vessels in color retinal fundus images, captured using fundus cameras, are often affected by illumination variations and noise, making it difficult to preserve vascular integrity and posing a significant challenge for vessel segmentation. In this paper, we propose HM-Mamba, a novel hierarchical multi-scale Mamba-based architecture that incorporates tubular structure-aware convolution to extract both local and global vascular features for retinal vessel segmentation. First, we introduce a tubular structure-aware convolution to reinforce vessel continuity and integrity. Building on this, we design a multi-scale fusion module that aggregates features across varying receptive fields, enhancing the model’s robustness in representing both primary trunks and fine branches. Second, we integrate multi-branch Fourier transform with the dynamic state modeling capability of Mamba to capture both long-range dependencies and multi-frequency information. This design enables robust feature representation and adaptive fusion, thereby enhancing the network’s ability to model complex spatial patterns. Furthermore, we propose a hierarchical multi-scale interactive Mamba block that integrates multi-level encoder features through gated Mamba-based global context modeling and residual connections, enabling effective multi-scale semantic fusion and reducing detail loss during downsampling. Extensive evaluations on five widely used benchmark datasets—DRIVE, CHASE_DB1, STARE, IOSTAR, and LES-AV—demonstrate the superior performance of HM-Mamba, yielding Dice coefficients of 0.8327, 0.8197, 0.8239, 0.8307, and 0.8426, respectively.

15 July 2025 in Neural Networks
Verified
Journal Article
Closed access
DTDongyuan Tian
Dongyuan Tian
YWYucheng Wang
Yucheng Wang
PGPeiliang Gong
Peiliang Gong
ZXZhewen Xu
Zhewen Xu
Zhenghua ChenZhenghua Chen
Zhenghua Chen
MWMin Wu
Min Wu

25 June 2026 in ACM Transactions on Architecture and Code Optimization
Verified
Journal Article
Open access
ZXZhewen Xu
Zhewen Xu
HLHongliang Li
Hongliang Li
JHJunze Han
Junze Han
HYHengshan Yue
Hengshan Yue
HZHairui Zhao
Hairui Zhao
XWXiaohui Wei
Xiaohui Wei
Distributed Graph Neural Network (DGNN) is a powerful tool in large-scale graph representation learning. However, high data-transfer overhead among workers in a DGNN training job confines its scalability and thus the overall performance. Vertex-wise historical embedding methods have demonstrated high potential to alleviate the problems, but still suffer from severe accuracy loss and limited performance scalability, which has been attributed to the information loss of critical channels in historical vertices and redundant information in local channels. This article explores the optimization of channel level and construct a quantitative accuracy model for channel-wise historical embedding. We propose Sift, a novel DGNN training framework, supporting channel-wise partial historical embedding with accuracy guarantee. Sift has three components: a historical embedding evaluator with channel-wise quantitative accuracy model, a sawtooth-like matrix rearrangement for accelerating message passing, and a hybrid parallel framework for overlapping communication overhead. Comprehensive experimental results show that Sift achieves near-linear parallel convergence speedup, outperforming the state-of-the-art baselines by up to 72% in total training performance and up to 21% in convergence speed.