12 citations · 29 across the 16 of their papers we have counts for
16 papers
Towards Automatic Evolution Tree Generation from Citation Graphs
Zexing Zhao, Yuntong Hu, Liang Zhao
Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publication. Existing taxonomy-indu…
Staypoint Detection from Noisy Trajectory Data [Experiment Paper]
Lance Kennedy, Hossein Amiri, Yueyang Liu +9
Detecting staypoints from raw trajectory data is fundamental to numerous spatial computing applications. This process transforms raw numeric sequences of geolocations into semantic…
CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs
Yuntong Hu, Zhihan Lei, Zhongjie Dai +4
Research question answering requires accurate retrieval and contextual understanding of scientific literature. However, current Retrieval-Augmented Generation (RAG) methods often s…
Transferable Unsupervised Outlier Detection Framework for Human Semantic Trajectories
Zheng Zhang, Hossein Amiri, Dazhou Yu +3
Semantic trajectories, which enrich spatial-temporal data with textual information such as trip purposes or location activities, are key for identifying outlier behaviors critical…
Taxonomy Tree Generation from Citation Graph
Yuntong Hu, Zhuofeng Li, Zheng Zhang +4
Constructing taxonomies from citation graphs is essential for organizing scientific knowledge, facilitating literature reviews, and identifying emerging research trends. However, m…
Representation Learning of Geometric Trees
Zheng Zhang, Allen Zhang, Ruth Nelson +2
Geometric trees are characterized by their tree-structured layout and spatially constrained nodes and edges, which significantly impacts their topological attributes. This inherent…
TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
Zhuofeng Li, Zixing Gou, Xiangnan Zhang +6
Text-Attributed Graphs (TAGs) augment graph structures with natural language descriptions, facilitating detailed depictions of data and their interconnections across various real-w…
TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations
Zheng Zhang, Yuntong Hu, Bo Pan +2
Text-Attributed Graphs (TAGs) enhance graph structures with natural language descriptions, enabling detailed representation of data and their relationships across a broad spectrum…
Link Prediction on Textual Edge Graphs
Chen Ling, Zhuofeng Li, Yuntong Hu +5
Textual-edge Graphs (TEGs), characterized by rich text annotations on edges, are increasingly significant in network science due to their ability to capture rich contextual informa…
GRAG: Graph Retrieval-Augmented Generation
Yuntong Hu, Zhihan Lei, Zheng Zhang +3
Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in…
Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs
Zheng Zhang, Fan Yang, Ziyan Jiang +5
Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts. This development is particularly crucial for tasks that involve retrievi…
Distilling Large Language Models for Text-Attributed Graph Learning
Bo Pan, Zheng Zhang, Yifei Zhang +2
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…
Transferable Deep Clustering Model
Zheng Zhang, Liang Zhao
Deep learning has shown remarkable success in the field of clustering recently. However, how to transfer a trained clustering model on a source domain to a target domain by leverag…
Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy
Zheng Zhang, Chen Zheng, Da Tang +5
This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks. The goal is to balance general lang…
Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data
Yuntong Hu, Zheng Zhang, Liang Zhao
Large language models (LLMs) have achieved impressive performance on many natural language processing tasks. However, their capabilities on graph-structured data remain relatively…
Large Language Models for Spatial Trajectory Patterns Mining
Zheng Zhang, Hossein Amiri, Zhenke Liu +2
Identifying anomalous human spatial trajectory patterns can indicate dynamic changes in mobility behavior with applications in domains like infectious disease monitoring and elderl…