Author name cluster

Liheng Ma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAMAS Conference 2026 Conference Paper

Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning

Yihong Wu
Liheng Ma
Muzhi Li
Jiaming Zhou
Lei Ding
Jianye Hao
Ho-fung Leung
Irwin King

Large Language Models (LLMs) equipped with modern Retrieval- Augmented Generation (RAG) systems often employ multi-turn interaction pipelines to interface with search engines for complex reasoning tasks. However, such multi-turn interactions inevitably produce long intermediate contexts, as context length grows exponentially with exploration depth. This leads to a well-known limitation of LLMs: their difficulty in effectively leveraging informationfromlongcontexts. ThisproblemisfurtheramplifiedinRAG systemsthatdependonin-contextlearning, wherefew-shotdemonstrations must also be included in the prompt, compounding the context-length bottleneck. To address these challenges, we propose Mujica-MyGo, a unified framework for efficient multi-turn reasoning in RAG. Inspired by the divide-and-conquer principle, we introduce Mujica (Multi-hop Joint Intelligence for Complex Question Answering), a multi-agent RAG workflow that decomposes multiturn interactions into cooperative sub-interactions, thereby mitigating long-context issues. To eliminate the dependency on in-context learning, we further develop MyGO (Minimalist Policy Gradient Optimization), a lightweight and efficient reinforcement learning algorithm that enables effective post-training of LLMs within complex RAG pipelines. We provide theoretical guarantees for MyGO’s convergence to the optimal policy. Empirical evaluations across diverse question-answering benchmarks—covering both text corpora and knowledge graphs—show that Mujica-MyGO achieves †qually contributed. This work is licensed under a Creative Commons Attribution International 4. 0 License. Proc. of the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026), C. Amato, L. Dennis, V. Mascardi, J. Thangarajah (eds.), May 25 – 29, 2026, Paphos, Cyprus. © 2026 International Foundation for Autonomous Agents and Multiagent Systems (www. ifaamas. org). https: //doi. org/10. 65109/QCQC1144 superior performance. Proofs, implementation details, and prompt templates are available in the extended version 1.

PDF

ICML Conference 2025 Conference Paper

SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting

Yitian Zhang
Liheng Ma
Antonios Valkanas
Boris N. Oreshkin
Mark Coates

Koopman operator theory provides a framework for nonlinear dynamical system analysis and time-series forecasting by mapping dynamics to a space 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.

Details

TMLR Journal 2025 Journal Article

Sparse Decomposition of Graph Neural Networks

Yaochen Hu
Mai Zeng
Ge Zhang
Pavel Rumiantsev
Liheng Ma
Yingxue Zhang
Mark Coates

Graph Neural Networks (GNN) exhibit superior performance in graph representation learning, but their inference cost can be high, due to an aggregation operation that can require a memory fetch for a very large number of nodes. This inference cost is the major obstacle to deploying GNN models with \emph{online prediction} to reflect the potentially dynamic node features. To address this, we propose an approach to reduce the number of nodes that are included during aggregation. We achieve this through a sparse decomposition, learning to approximate node representations using a weighted sum of linearly transformed features of a carefully selected subset of nodes within the extended neighbourhood. The approach achieves linear complexity with respect to the average node degree and the number of layers in the graph neural network. We introduce an algorithm to compute the optimal parameters for the sparse decomposition, ensuring an accurate approximation of the original GNN model, and present effective strategies to reduce the training time and improve the learning process. We demonstrate via extensive experiments that our method outperforms other baselines designed for inference speedup, achieving significant accuracy gains with comparable inference times for both node classification and spatio-temporal forecasting tasks.

PDF Details

ICML Conference 2024 Conference Paper

CKGConv: General Graph Convolution with Continuous Kernels

Liheng Ma
Soumyasundar Pal
Yitian Zhang
Jiaming Zhou
Yingxue Zhang 0001
Mark Coates

The existing definitions of graph convolution, either from spatial or spectral perspectives, are inflexible and not unified. Defining a general convolution operator in the graph domain is challenging due to the lack of canonical coordinates, the presence of irregular structures, and the properties of graph symmetries. In this work, we propose a novel and general graph convolution framework by parameterizing the kernels as continuous functions of pseudo-coordinates derived via graph positional encoding. We name this Continuous Kernel Graph Convolution (CKGConv). Theoretically, we demonstrate that CKGConv is flexible and expressive. CKGConv encompasses many existing graph convolutions, and exhibits a stronger expressiveness, as powerful as graph transformers in terms of distinguishing non-isomorphic graphs. Empirically, we show that CKGConv-based Networks outperform existing graph convolutional networks and perform comparably to the best graph transformers across a variety of graph datasets. The code and models are publicly available at https: //github. com/networkslab/CKGConv.

Details

ICML Conference 2023 Conference Paper

Graph Inductive Biases in Transformers without Message Passing

Liheng Ma
Chen Lin 0003
Derek Lim
Adriana Romero-Soriano
Puneet Kumar Dokania
Mark Coates
Philip H. S. Torr
Ser-Nam Lim

Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph Transformers that use message-passing inherit known issues of message-passing, and differ significantly from Transformers used in other domains, thus making transfer of research advances more difficult. On the other hand, Graph Transformers without message-passing often perform poorly on smaller datasets, where inductive biases are more crucial. To bridge this gap, we propose the Graph Inductive bias Transformer (GRIT) — a new Graph Transformer that incorporates graph inductive biases without using message passing. GRIT is based on several architectural changes that are each theoretically and empirically justified, including: learned relative positional encodings initialized with random walk probabilities, a flexible attention mechanism that updates node and node-pair representations, and injection of degree information in each layer. We prove that GRIT is expressive — it can express shortest path distances and various graph propagation matrices. GRIT achieves state-of-the-art empirical performance across a variety of graph datasets, thus showing the power that Graph Transformers without message-passing can deliver.

Details

AAAI Conference 2021 Conference Paper

Knowledge-Enhanced Top-K Recommendation in Poincaré Ball

Chen Ma
Liheng Ma
Yingxue Zhang
Haolun Wu
Xue Liu
Mark Coates

Personalized recommender systems are increasingly important as more content and services become available and users struggle to identify what might interest them. Thanks to the ability for providing rich information, knowledge graphs (KGs) are being incorporated to enhance the recommendation performance and interpretability. To effectively make use of the knowledge graph, we propose a recommendation model in the hyperbolic space, which facilitates the learning of the hierarchical structure of knowledge graphs. Furthermore, a hyperbolic attention network is employed to determine the relative importances of neighboring entities of a certain item. In addition, we propose an adaptive and finegrained regularization mechanism to adaptively regularize items and their neighboring representations. Via a comparison using three real-world datasets with stateof-the-art methods, we show that the proposed model outperforms the best existing models by 2-16% in terms of NDCG@K on Top-K recommendation.

PDF Details

ICML Conference 2021 Conference Paper

RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting

Soumyasundar Pal
Liheng Ma
Yingxue Zhang 0001
Mark Coates

Spatio-temporal forecasting has numerous applications in analyzing wireless, traffic, and financial networks. Many classical statistical models often fall short in handling the complexity and high non-linearity present in time-series data. Recent advances in deep learning allow for better modelling of spatial and temporal dependencies. While most of these models focus on obtaining accurate point forecasts, they do not characterize the prediction uncertainty. In this work, we consider the time-series data as a random realization from a nonlinear state-space model and target Bayesian inference of the hidden states for probabilistic forecasting. We use particle flow as the tool for approximating the posterior distribution of the states, as it is shown to be highly effective in complex, high-dimensional settings. Thorough experimentation on several real world time-series datasets demonstrates that our approach provides better characterization of uncertainty while maintaining comparable accuracy to the state-of-the-art point forecasting methods.

Details

AAAI Conference 2020 Conference Paper

Memory Augmented Graph Neural Networks for Sequential Recommendation

Chen Ma
Liheng Ma
Yingxue Zhang
Jianing Sun
Xue Liu
Mark Coates

The chronological order of user-item interactions can reveal time-evolving and sequential user behaviors in many recommender systems. The items that users will interact with may depend on the items accessed in the past. However, the substantial increase of users and items makes sequential recommender systems still face non-trivial challenges: (1) the hardness of modeling the short-term user interests; (2) the difﬁculty of capturing the long-term user interests; (3) the effective modeling of item co-occurrence patterns. To tackle these challenges, we propose a memory augmented graph neural network (MA-GNN) to capture both the long- and short-term user interests. Speciﬁcally, we apply a graph neural network to model the item contextual information within a short-term period and utilize a shared memory network to capture the long-range dependencies between items. In addition to the modeling of user interests, we employ a bilinear function to capture the co-occurrence patterns of related items. We extensively evaluate our model on ﬁve real-world datasets, comparing with several state-of-the-art methods and using a variety of performance metrics. The experimental results demonstrate the effectiveness of our model for the task of Top-K sequential recommendation.

PDF Details