Portrait of Liheng Ma

Liheng Ma

PhD - McGill University
Supervisor
Mark Coates
Research Topics
Geometric Deep Learning
Graph Neural Networks
Learning on Graphs
Recommender Systems
Time Series
Website
Google Scholar
GitHub

Publications

SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting
Yitian Zhang
Liheng Ma
Antonios Valkanas
Boris Oreshkin
Mark Coates
Koopman operator theory provides a framework for nonlinear dynamical system analysis and time-series forecasting by mapping dynamics to a sp… (see more)ace of real-valued measurement functions, enabling a linear operator representation. Despite the advantage of linearity, the operator is generally infinite-dimensional. Therefore, the objective is to learn measurement functions that yield a tractable finite-dimensional Koopman operator approximation. In this work, we establish a connection between Koopman operator approximation and linear Recurrent Neural Networks (RNNs), which have recently demonstrated remarkable success in sequence modeling. We show that by considering an extended state consisting of lagged observations, we can establish an equivalence between a structured Koopman operator and linear RNN updates. Building on this connection, we present SKOLR, which integrates a learnable spectral decomposition of the input signal with a multilayer perceptron (MLP) as the measurement functions and implements a structured Koopman operator via a highly parallel linear RNN stack. Numerical experiments on various forecasting benchmarks and dynamical systems show that this streamlined, Koopman-theory-based design delivers exceptional performance. Our code is available at: https://github.com/networkslab/SKOLR.
2025-05-01
ICML.cc/2025/Conference (poster)
doi.org
openreview.net
Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data
Jiaming Zhou
Abbas Ghaddar
Ge Zhang
Liheng Ma
Yaochen Hu
Soumyasundar Pal
Mark Coates
Bin Wang
Yingxue Zhang
Jianye HAO
Despite recent advances in training and prompting strategies for Large Language Models (LLMs), these models continue to face challenges with… (see more) complex logical reasoning tasks that involve long reasoning chains. In this work, we explore the potential and limitations of using graph-based synthetic reasoning data as training signals to enhance LLMs' reasoning capabilities. Our extensive experiments, conducted on two established natural language reasoning tasks -- inductive reasoning and spatial reasoning -- demonstrate that supervised fine-tuning (SFT) with synthetic graph-based reasoning data effectively enhances LLMs' reasoning performance without compromising their effectiveness on other standard evaluation benchmarks.
2024-09-19
ArXiv (preprint)
doi.org
arxiv.org