Bo Xiong

All Publications

• Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Jin, M., Shi, G., Li, Y., Xiong, B., Zhou, T., Salim, F. D., Zhao, L., Wu, L., Wen, Q., Pan, S. 2025; 47 (6): 4926-4939

  Abstract

  Time series forecasting has remained a focal point due to its vital applications in sectors such as energy management and transportation planning. Spectral-temporal graph neural network is a promising abstraction underlying most time series forecasting models that are based on graph neural networks (GNNs). However, more is needed to know about the underpinnings of this branch of methods. In this paper, we establish a theoretical framework that unravels the expressive power of spectral-temporal GNNs. Our results show that linear spectral-temporal GNNs are universal under mild assumptions, and their expressive power is bounded by our extended first-order Weisfeiler-Leman algorithm on discrete-time dynamic graphs. To make our findings useful in practice on valid instantiations, we discuss related constraints in detail and outline a theoretical blueprint for designing spatial and temporal modules in spectral domains. Building on these insights and to demonstrate how powerful spectral-temporal GNNs are based on our framework, we propose a simple instantiation named Temporal Graph Gegenbauer Convolution (TGGC), which significantly outperforms most existing models with only linear components and shows better model efficiency.

  View details for DOI 10.1109/TPAMI.2025.3545671

  View details for Web of Science ID 001484716600031

  View details for PubMedID 40031664

• From Tokens to Lattices: Emergent Lattice Structures in Language Models International Conference of Learning Representation Xiong, B., Staab, S. 2025
• HypMix: Hyperbolic Representation Learning for Graphs with Mixed Hierarchical and Non-hierarchical Structures. Proceedings of the ... ACM International Conference on Information & Knowledge Management. ACM International Conference on Information and Knowledge Management Lee, E. W., Xiong, B., Yang, C., Ho, J. C. 2024; 2024: 3852-3856

  Abstract

  Heterogeneous networks contain multiple types of nodes and links, with some link types encapsulating hierarchical structure over entities. Hierarchical relationships can codify information such as subcategories or one entity being subsumed by another and are often used for organizing conceptual knowledge into a tree-structured graph. Hyperbolic embedding models learn node representations in a hyperbolic space suitable for preserving the hierarchical structure. Unfortunately, current hyperbolic embedding models only implicitly capture the hierarchical structure, failing to distinguish between node types, and they only assume a single tree. In practice, many networks contain a mixture of hierarchical and non-hierarchical structures, and the hierarchical relations may be represented as multiple trees with complex structures, such as sharing certain entities. In this work, we propose a new hyperbolic representation learning model that can handle complex hierarchical structures and also learn the representation of both hierarchical and non-hierarchic structures. We evaluate our model on several datasets, including identifying relevant articles for a systematic review, which is an essential tool for evidence-driven medicine and node classification.

  View details for DOI 10.1145/3627673.3679940

  View details for PubMedID 40018085

  View details for PubMedCentralID PMC11867734

• NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning Xiong, B., Nayyeri, M., Luo, L., Wang, Z., Pan, S., Staab, S., Wooldridge, M., Dy, J., Natarajan, S. ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2024: 9205-9213

  View details for Web of Science ID 001239938200145

• Reasoning beyond Triples: Recent Advances in Knowledge Graph Embeddings Xiong, B., Nayyeri, M., Daza, D., Cochez, M., ACM ASSOC COMPUTING MACHINERY. 2023: 5228-5231

  View details for DOI 10.1145/3583780.3615294

  View details for Web of Science ID 001161549505049

• HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting Lu, J., Shen, J., Xiong, B., Ma, W., Staab, S., Yang, C., ACM ASSOC COMPUTING MACHINERY. 2023: 2052-2056

  Abstract

  Medical decision-making processes can be enhanced by comprehensive biomedical knowledge bases, which require fusing knowledge graphs constructed from different sources via a uniform index system. The index system often organizes biomedical terms in a hierarchy to provide the aligned entities with fine-grained granularity. To address the challenge of scarce supervision in the biomedical knowledge fusion (BKF) task, researchers have proposed various unsupervised methods. However, these methods heavily rely on ad-hoc lexical and structural matching algorithms, which fail to capture the rich semantics conveyed by biomedical entities and terms. Recently, neural embedding models have proved effective in semantic-rich tasks, but they rely on sufficient labeled data to be adequately trained. To bridge the gap between the scarce-labeled BKF and neural embedding models, we propose HiPrompt, a supervision-efficient knowledge fusion framework that elicits the few-shot reasoning ability of large language models through hierarchy-oriented prompts. Empirical results on the collected KG-Hi-BKF benchmark datasets demonstrate the effectiveness of HiPrompt.

  View details for DOI 10.1145/3539618.3591997

  View details for Web of Science ID 001118084002020

  View details for PubMedID 38352127

  View details for PubMedCentralID PMC10863609

• Hyperbolic Graph Neural Networks: A Tutorial on Methods and Applications Zhou, M., Yang, M., Xiong, B., Xiong, H., King, I., ACM ASSOC COMPUTING MACHINERY. 2023: 5843-5844

  View details for DOI 10.1145/3580305.3599562

  View details for Web of Science ID 001118896305105

• Shrinking Embeddings for Hyper-Relational Knowledge Graphs Xiong, B., Nayyeri, M., Pan, S., Staab, S., Rogers, A., Boyd-Graber, J., Okazaki, N. ASSOC COMPUTATIONAL LINGUISTICS-ACL. 2023: 13306-13320

  View details for Web of Science ID 001190962505005

• Pseudo-Riemannian Graph Convolutional Networks Xiong, B., Zhu, S., Potyka, N., Pan, S., Zhou, C., Staab, S., Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2022

  View details for Web of Science ID 001215469507014

• Hyperbolic Embedding Inference for Structured Multi-Label Prediction Xiong, B., Cochez, M., Nayyeri, M., Staab, S., Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2022

  View details for Web of Science ID 001213927504027

• Faithful Embeddings for ε<i>L</i><SUP>++</SUP> Knowledge Bases Xiong, B., Potyka, N., Tran, T., Nayyeri, M., Staab, S., Sattler, U., Hogan, A., Keet, M., Presutti, Almeida, J. P., Takeda, H., Monnin, P., Pirro, G., DAmato, C. SPRINGER INTERNATIONAL PUBLISHING AG. 2022: 22-38

  View details for DOI 10.1007/978-3-031-19433-7_2

  View details for Web of Science ID 000886782800002

• Time-aware Entity Alignment using Temporal Relational Attention Xu, C., Su, F., Xiong, B., Lehmann, J., ACM ASSOC COMPUTING MACHINERY. 2022: 788-797

  View details for DOI 10.1145/3485447.3511922

  View details for Web of Science ID 000852713000079

• Ultrahyperbolic Knowledge Graph Embeddings Xiong, B., Zhu, S., Nayyeri, M., Xu, C., Pan, S., Zhou, C., Staab, S., ACM ASSOC COMPUTING MACHINERY. 2022: 2130-2139

  View details for DOI 10.1145/3534678.3539333

  View details for Web of Science ID 001119000302019