ZZZheng Zhang

Zheng Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zheng Zhang has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Self-Supervised Contrastive Learning for Individual and Collective Outlier Detection in Semantic Trajectories

    by Xingzu Zhan, Hossein Amiri, Zheng Zhang, Dazhou Yu, Yuntong Hu, Honghang Chen, Liang Zhao, Andreas Züfle

    Semantic trajectories enrich spatiotemporal data with textual semantics such as trip purposes and activities at points of interest, enabling the discovery of outlier behaviors relevant to public health, social security, and urban planning. Existing detectors often depend on hand crafted rules and rarely fuse space, time, and text in a transferable way. We propose TOD4Traj , an unsupervised and transfer ready framework for human semantic trajectories that detects anomalies at both the individual and collective levels. TOD4Traj first unifies modalities through spatiotemporal to semantic contrastive alignment so heterogeneous signals share a common representation. It then learns regular mobility via temporal contrastive learning that aligns the same weekday and separates different weekdays. Deviations are scored by combining a consistency score against a user’s own history with a population score based on a small set of learned centroids that capture low rank mobility regularities. For group analysis, we introduce a population level contrastive objective and a collective outlier score that compare a date’s population embedding with historical weekday prototypes, revealing collective abnormality. Across simulated cities and a GeoLife derived dataset, TOD4Traj consistently outperforms strong baselines on both tasks and shows robust zero shot transfer across cities, demonstrating effectiveness, robustness, and adaptability for outlier detection in human semantic trajectories.

  • Open Access

    Efficient Deep Generative Models for Spatial Networks via Spanning Tree Sampler

    by Xiaojie Guo, Yuanqi Du, Zheng Zhang, Liang Zhao

    In the big data era, spatial-network data has become increasingly important and popular in many real-world objects, ranging from micro-scale (e.g., molecule structures), to middle-scale (e.g., biological neural networks), to macro-scale (e.g., mobility networks). Spatial networks consist of nodes and edges that are embedded in a geometric space. Although, it is critical to model and understand the generative process of spatial networks, this task remains largely under-explored due to the significant difficulty in automatically modeling and distinguishing the dependency and relevance among various spatial and network semantic factors. In addition, containing both spatial and network information makes the modeling of spatial networks bear large time and memory cost, especially for large graphs. To address the aforementioned challenges, we first propose a novel objective for joint spatial-network disentangled representation learning from the perspective of information bottleneck as well as a novel progressive optimization algorithm to optimize the intractable objective. Based on this, a Spatial-Network Disentangled Variational Autoencoder (SND-VAE) is proposed to discover the independent and dependent latent factors of spatial and networks. To reduce the time complexity, an efficient version SND-VAE-light is proposed, which is based on a novel Efficient Spatial-Network Message Passing Neural Network (ES-MPNN). Qualitative and quantitative experiments on both synthetic and real-world datasets with various scales of graph size demonstrate the superiority of the proposed model over the state-of-the-arts by up to 66.9% for graph generation and 37.3% for interpretability. In addition, the ES-MPNN is also proved to reduce the time complexity of the encoder in the generative model from cubic to linear growth (The implementation of this work can be found at https://github.com/xguo7/SND-VAE ).


  • Open Access

    CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs

    by Yuntong Hu, Zhihan Lei, Zhongjie Dai, Allen Zhang, Abhinav Angirekula, Zheng Zhang, Liang Zhao


  • Open Access

    CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs

    by Yuntong Hu, Zhihan Lei, Zhongjie Dai, Allen Zhang, Abhinav Angirekula, Zheng Zhang, Liang Zhao

    Research question answering requires accurate retrieval and contextual understanding of scientific literature. However, current Retrieval-Augmented Generation (RAG) methods often struggle to balance complex document relationships with precise information retrieval. In this paper, we introduce Contextualized Graph Retrieval-Augmented Generation (CG-RAG), a novel framework that integrates sparse and dense retrieval signals within graph structures to enhance retrieval efficiency and subsequently improve generation quality for research question answering. First, we propose a contextual graph representation for citation graphs, effectively capturing both explicit and implicit connections within and across documents. Next, we introduce Lexical-Semantic Graph Retrieval (LeSeGR), which seamlessly integrates sparse and dense retrieval signals with graph encoding. It bridges the gap between lexical precision and semantic understanding in citation graph retrieval, demonstrating generalizability to existing graph retrieval and hybrid retrieval methods. Finally, we present a context-aware generation strategy that utilizes the retrieved graph-structured information to generate precise and contextually enriched responses using large language models (LLMs). Extensive experiments on research question answering benchmarks across multiple domains demonstrate that our CG-RAG framework significantly outperforms RAG methods combined with various state-of-the-art retrieval approaches, delivering superior retrieval accuracy and generation quality.

  • Open Access

    Transferable Unsupervised Outlier Detection Framework for Human Semantic Trajectories

    by Zheng Zhang, Hossein Amiri, Dazhou Yu, Yuntong Hu, Liang Zhao, 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.


  • Open Access

    Large Language Models for Spatial Trajectory Patterns Mining

    by Zheng Zhang, Hossein Amiri, Zhenke Liu, Liang Zhao, Andreas Zuefle

    Identifying anomalous human spatial trajectory patterns can indicate dynamic changes in mobility behavior with applications in domains like infectious disease monitoring and elderly care. Recent advancements in large language models (LLMs) have demonstrated their ability to reason in a manner akin to humans. This presents significant potential for analyzing temporal patterns in human mobility. In this paper, we conduct empirical studies to assess the capabilities of leading LLMs like GPT-4 and Claude-2 in detecting anomalous behaviors from mobility data, by comparing to specialized methods. Our key findings demonstrate that LLMs can attain reasonable anomaly detection performance even without any specific cues. In addition, providing contextual clues about potential irregularities could further enhances their prediction efficacy. Moreover, LLMs can provide reasonable explanations for their judgments, thereby improving transparency. Our work provides insights on the strengths and limitations of LLMs for human spatial trajectory analysis.


  • Open Access

    Distilling Large Language Models for Text-Attributed Graph Learning

    by Bo Pan, Zheng Zhang, Yifei Zhang, Yuntong Hu, 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.


  • Open Access

    Representation Learning of Geometric Trees

    by Zheng Zhang, Allen Zhang, Ruth Nelson, Giorgio Ascoli, Liang Zhao

    Geometric trees are characterized by their tree-structured layout and spatially constrained nodes and edges, which significantly impacts their topological attributes. This inherent hierarchical structure plays a crucial role in domains such as neuron morphology and river geomorphology, but traditional graph representation methods often overlook these specific characteristics of tree structures. To address this, we introduce a new representation learning framework tailored for geometric trees. It first features a unique message passing neural network, which is both provably geometrical structure-recoverable and rotation-translation invariant. To address the data label scarcity issue, our approach also includes two innovative training targets that reflect the hierarchical ordering and geometric structure of these geometric trees. This enables fully self-supervised learning without explicit labels. We validate our method's effectiveness on eight real-world datasets, demonstrating its capability to represent geometric trees.