Yuntong Hu

Yuntong Hu

Auto-generated profile, based on publicly available information

Yuntong Hu

Emory University, Atlanta, GA, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
3 June 2022 in Applied Soft Computing
Verified
Journal Article
Closed access
YHYuntong Hu
Yuntong Hu
FXFuyuan Xiao
Fuyuan Xiao

8 February 2022 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
YHYuntong Hu
Yuntong Hu
FXFuyuan Xiao
Fuyuan Xiao

21 October 2024
Verified
Conference Paper
Open access
BPBo Pan
Bo Pan
ZZZheng Zhang
Zheng Zhang
YZYifei Zhang
Yifei Zhang
YHYuntong Hu
Yuntong Hu
LZLiang Zhao
Liang Zhao
Text-Attributed Graphs (TAGs) are graphs of connected textual documents. Graph models can efficiently learn TAGs, but their training heavily relies on human-annotated labels, which are scarce or even unavailable in many applications. Large language models (LLMs) have recently demonstrated remarkable capabilities in few-shot and zero-shot TAG learning, but they suffer from scalability, cost, and privacy issues. Therefore, in this work, we focus on synergizing LLMs and graph models with their complementary strengths by distilling the power of LLMs into a local graph model on TAG learning. To address the inherent gaps between LLMs (generative models for texts) and graph models (discriminative models for graphs), we propose first to let LLMs teach an interpreter with rich rationale and then let a student model mimic the interpreter's reasoning without LLMs' rationale. We convert LLM's textual rationales to multi-level graph rationales to train the interpreter model and align the student model with the interpreter model based on the features of TAGs. Extensive experiments validate the efficacy of our proposed framework.

29 October 2024
Verified
Conference Paper
Open access
ZZZheng Zhang
Zheng Zhang
HAHossein Amiri
Hossein Amiri
DYDazhou Yu
Dazhou Yu
YHYuntong Hu
Yuntong Hu
LZLiang Zhao
Liang Zhao
AZAndreas Züfle
Andreas Züfle
Semantic trajectories, which enrich spatial-temporal data with textual information such as trip purposes or location activities, are key for identifying outlier behaviors critical to healthcare, social security, and urban planning. Traditional outlier detection relies on heuristic rules, which requires domain knowledge and limits its ability to identify unseen outliers. Besides, there lacks a comprehensive approach that can jointly consider multi-modal data across spatial, temporal, and textual dimensions. Addressing the need for a domain-agnostic model, we propose the Transferable Outlier Detection for Human Semantic Trajectories (TOD4Traj) framework. TOD4Traj first introduces a modality feature unification module to align diverse data feature representations, enabling the integration of multi-modal information and enhancing transferability across different datasets. A contrastive learning module is further proposed for identifying regular mobility patterns both temporally and across populations, allowing for a joint detection of outliers based on individual consistency and group majority patterns. Our experimental results have shown TOD4Traj's superior performance over existing models, demonstrating its effectiveness and adaptability in detecting human trajectory outliers across various datasets.

24 August 2024
Verified
Conference Paper
Open access
DYDazhou Yu
Dazhou Yu
YHYuntong Hu
Yuntong Hu
Yun LiYun Li
Yun Li
LZLiang Zhao
Liang Zhao
Polygon representation learning is essential for diverse applications, encompassing tasks such as shape coding, building pattern classification, and geographic question answering. While recent years have seen considerable advancements in this field, much of the focus has been on single polygons, overlooking the intricate inner- and inter-polygonal relationships inherent in multipolygons. To address this gap, our study introduces a comprehensive framework specifically designed for learning representations of polygonal geometries, particularly multipolygons. Central to our approach is the incorporation of a heterogeneous visibility graph, which seamlessly integrates both inner- and inter-polygonal relationships. To enhance computational efficiency and minimize graph redundancy, we implement a heterogeneous spanning tree sampling method. Additionally, we devise a rotation-translation invariant geometric representation, ensuring broader applicability across diverse scenarios. Finally, we introduce Multipolygon-GNN, a novel model tailored to leverage the spatial and semantic heterogeneity inherent in the visibility graph. Experiments on five real-world and synthetic datasets demonstrate its ability to capture informative representations for polygonal geometries.

13 July 2025
Verified
Conference Paper
Open access
YHYuntong Hu
Yuntong Hu
ZLZhihan Lei
Zhihan Lei
ZDZhongjie Dai
Zhongjie Dai
AZAllen Zhang
Allen Zhang
AAAbhinav Angirekula
Abhinav Angirekula
LZLiang Zhao
Liang Zhao