Menglin Yang

About

Background. I am currently an assistant professor at Thrust of Artificial Intelligence at HKUSTGZ. I was a Postdoc at Yale University, working with Prof. Rex Ying. Before that, I obtained my Ph.D. from The Chinese University of Hong Kong, supervised by Prof. Irwin King.

Information about PhD student recruitment can be found on pages in Chinese Version, or English Version.

Research Interests. My research is primarily focused on exploring the connection and alignment between the learning space, especially the hyperbolic space, and the underlying geometries, structures, and patterns in different types of data.

Recently, I have been working on the following topics:

(1) Hyperbolic representation learning, curvature adaptive learning, differential geometry

(2) Foundation models, generative model, alignment across multi-source data, non-Euclidean space for foundation models

(3) Recommender systems, network sciences, and AI4SCI

Feel free to reach out to menglinyang[at]hkust-gz.edu.cn or digailab[at]outlook.com if you have anything you would like to discuss.

Call for Papers on non-Euclidean representation learning, geometric deep learning, and large foundation models, as well as web-related applications:

🔥 NEGEL workshop at TheWebConf 2025 (Click)

2025-01-15: Paper submission deadline

Submission site: https://openreview.net/group?id=ACM.org/TheWebConf/2025/Workshop/NEGEL

Venue: International Convention & Exhibition Centre (ICC), Sydney, Australia

Timezone: Anywhere On Earth (UTC-12)

New papers, blogs, and books on hyperbolic representation and deep learning topics are shared in the following slack channel and GitHub repo. Welcome to join and share more on this fascinating research:

Hyperbolic Representation and Deep Learning Slack Channel (Click)

Awesome Hyperbolic Representation and Deep Learning GitHub Repository (Click)

Selected Publications

KDD ’24

Hypformer: Exploring Efficient Transformer in Hyperbolic space

Menglin Yang, Harshit Verma, Delvin Ce Zhang, Jiahong Liu, Irwin King, and Rex Ying

KDD, 2024

Abs PDF Code

Hyperbolic geometry have shown significant potential in modeling complex structured data, particularly those with underlying tree-like and hierarchical structures. Despite the impressive performance of various hyperbolic neural networks across numerous domains, research on adapting the Transformer to hyperbolic space remains limited. Previous attempts have mainly focused on modifying self-attention modules in the Transformer. However, these efforts have fallen short of developing a complete hyperbolic Transformer. This stems primarily from: (i) the absence of well-defined modules in hyperbolic space, including linear transformation layers, LayerNorm layers, activation functions, dropout operations, etc. (ii) the quadratic time complexity of the existing hyperbolic self-attention module w.r.t the number of input tokens, which hinders its scalability. To address these challenges, we propose, Hypformer, a novel hyperbolic Transformer based on the Lorentz model of hyperbolic geometry. In Hypformer, we introduce two foundational blocks that define the essential modules of the Transformer in hyperbolic space. Furthermore, we develop a linear self-attention mechanism in hyperbolic space, enabling hyperbolic Transformer to process billion-scale graph data and long-sequence inputs for the first time. Our experimental results confirm the effectiveness and efficiency of Hypformer across various datasets, demonstrating its potential as an effective and scalable solution for large-scale data representation and large models.
Preprint ’24

Hyperbolic Fine-tuning for Large Language Models

Menglin Yang, Aosong Feng, Bo Xiong, Jiahong Liu, Irwin King, and Rex Ying

Preprint, 2024

PDF Code
ICML ’23

Hierarchical Learning in Hyperbolic Space: Revisit and Beyond

Menglin Yang, Min Zhou, Rex Ying, Yankai Chen, and Irwin King

ICML, 2023

PDF Code
KDD ’22

HICF: Hyperbolic Informative Collaborative Filtering

Menglin Yang, Zhihao Li, Min Zhou, Jiahong Liu, and Irwin King

KDD, 2022

PDF Code
WWW ’22

HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization

Menglin Yang, Min Zhou, Jiahong Liu, Defu Lian, and Irwin King

WWW, 2022

PDF Code
KDD ’21

Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space

Menglin Yang, Min Zhou, Marcus Kalander, Zengfeng Huang, and Irwin King

KDD, 2021

PDF Code