Yizhen Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yizhen Zheng has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Shirui Pan
Griffith University, Australia
20 shared publications - Huan Yee Koh
Monash University
5 shared publications - Yixin Liu
Griffith University, Australia
5 shared publications - Jiaxin Ju
Griffith University
4 shared publications - Vincent Cheng Siong Lee
Monash University, Melbourne, VIC, Australia
4 shared publications - Di Jin
College of Intelligence and Computing, Tianjin University, Tianjin, China
3 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12739-12750
UniEdit: A Graph-based MoE Alternative to Sequence Generation for Molecular Editing
Recently, Large Language Models (LLMs) have become the dominant paradigm for molecular editing due to their strong generalization capabilities across diverse tasks. However, treating molecules as 1D text strings (SMILES) introduces significant challenges in controllability and structural validity. In this paper, we question whether sequence generation is truly optimal for this topological task. We propose UniEdit, a Unified Graph-based Mixture-of-Experts (MoE) Molecular Editing model that offers a robust alternative to LLMs. Diverging from the generative approach, UniEdit reformulates molecular editing as a hierarchical node-level classification task. By predicting discrete edit actions (e.g., Add, Remove, Replace) directly on the graph, our model ensures topological precision by design. To handle conflicting multi-objective constraints within a single framework, we incorporate a Mixture-of-Experts architecture that dynamically routes tasks to specialized components. Extensive experiments across 28 diverse tasks demonstrate that UniEdit significantly outperforms sequence-based baselines. Furthermore, a preliminary scaling study reveals that our graph-based approach benefits consistently from increased model capacity, suggesting a scalable path toward general-purpose molecular editing. Our code is available at https://github.com/jiajunyu1999/GraphEditing.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12739-12750
Open AccessUniEdit: A Graph-based MoE Alternative to Sequence Generation for Molecular Editing
Recently, Large Language Models (LLMs) have become the dominant paradigm for molecular editing due to their strong generalization capabilities across diverse tasks. However, treating molecules as 1D text strings (SMILES) introduces significant challenges in controllability and structural validity. In this paper, we question whether sequence generation is truly optimal for this topological task. We propose UniEdit, a Unified Graph-based Mixture-of-Experts (MoE) Molecular Editing model that offers a robust alternative to LLMs. Diverging from the generative approach, UniEdit reformulates molecular editing as a hierarchical node-level classification task. By predicting discrete edit actions (e.g., Add, Remove, Replace) directly on the graph, our model ensures topological precision by design. To handle conflicting multi-objective constraints within a single framework, we incorporate a Mixture-of-Experts architecture that dynamically routes tasks to specialized components. Extensive experiments across 28 diverse tasks demonstrate that UniEdit significantly outperforms sequence-based baselines. Furthermore, a preliminary scaling study reveals that our graph-based approach benefits consistently from increased model capacity, suggesting a scalable path toward general-purpose molecular editing. Our code is available at https://github.com/jiajunyu1999/GraphEditing.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12643-12654
Natural Language-Powered Functional Protein Sequence and Structure Co-Design with Multi-Modal Knowledge Fusion
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12643-12654
Open AccessNatural Language-Powered Functional Protein Sequence and Structure Co-Design with Multi-Modal Knowledge Fusion
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 9, 7437-7445
M^2LLM: Multi-view Molecular Representation Learning with Large Language Models
Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose M^2LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that M^2LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 9, 7437-7445
Open AccessM^2LLM: Multi-view Molecular Representation Learning with Large Language Models
Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose M^2LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that M^2LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.
- Open Access
$\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models
Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose $\text{M}^{2}$LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that $\text{M}^{2}$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.
Open Access$\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models
Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose $\text{M}^{2}$LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that $\text{M}^{2}$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.
- 18 June 2025
- Published by Springer Nature
- p. 275-287
Uni-MRL: Unified MultiModal Molecular Representation Learning with Large Language Models and Graph Neural Networks
- 18 June 2025
- Published by Springer Nature
- p. 275-287
Uni-MRL: Unified MultiModal Molecular Representation Learning with Large Language Models and Graph Neural Networks
- 18 June 2025
- Published by Springer Nature
- p. 224-236
SpecG: A Spectral-Based Framework for Effective Graph Pretraining and Knowledge Transfer
- 18 June 2025
- Published by Springer Nature
- p. 224-236
SpecG: A Spectral-Based Framework for Effective Graph Pretraining and Knowledge Transfer
- Open Access
ModuLM: Enabling Modular and Multimodal Molecular Relational Learning with Large Language Models
Molecular Relational Learning (MRL) aims to understand interactions between molecular pairs, playing a critical role in advancing biochemical research. With the recent development of large language models (LLMs), a growing number of studies have explored the integration of MRL with LLMs and achieved promising results. However, the increasing availability of diverse LLMs and molecular structure encoders has significantly expanded the model space, presenting major challenges for benchmarking. Currently, there is no LLM framework that supports both flexible molecular input formats and dynamic architectural switching. To address these challenges, reduce redundant coding, and ensure fair model comparison, we propose ModuLM, a framework designed to support flexible LLM-based model construction and diverse molecular representations. ModuLM provides a rich suite of modular components, including 8 types of 2D molecular graph encoders, 11 types of 3D molecular conformation encoders, 7 types of interaction layers, and 7 mainstream LLM backbones. Owing to its highly flexible model assembly mechanism, ModuLM enables the dynamic construction of over 50,000 distinct model configurations. In addition, we provide comprehensive results to demonstrate the effectiveness of ModuLM in supporting LLM-based MRL tasks.
Open AccessModuLM: Enabling Modular and Multimodal Molecular Relational Learning with Large Language Models
Molecular Relational Learning (MRL) aims to understand interactions between molecular pairs, playing a critical role in advancing biochemical research. With the recent development of large language models (LLMs), a growing number of studies have explored the integration of MRL with LLMs and achieved promising results. However, the increasing availability of diverse LLMs and molecular structure encoders has significantly expanded the model space, presenting major challenges for benchmarking. Currently, there is no LLM framework that supports both flexible molecular input formats and dynamic architectural switching. To address these challenges, reduce redundant coding, and ensure fair model comparison, we propose ModuLM, a framework designed to support flexible LLM-based model construction and diverse molecular representations. ModuLM provides a rich suite of modular components, including 8 types of 2D molecular graph encoders, 11 types of 3D molecular conformation encoders, 7 types of interaction layers, and 7 mainstream LLM backbones. Owing to its highly flexible model assembly mechanism, ModuLM enables the dynamic construction of over 50,000 distinct model configurations. In addition, we provide comprehensive results to demonstrate the effectiveness of ModuLM in supporting LLM-based MRL tasks.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (12) , 12443-12451
A Label-free Heterophily-guided Approach for Unsupervised Graph Fraud Detection
Graph fraud detection (GFD) has rapidly advanced in protecting online services by identifying malicious fraudsters. Recent supervised GFD research highlights that heterophilic connections between fraudster and user greatly impacts detection performance, where the fraudsters tend to camouflage themselves by building more connections to benign users. Despite their promising performance, their label reliance limits its application in unsupervised scenarios; Additionally, accurately capturing complex and diverse heterophily patterns without labels poses a further challenge. Therefore, we propose a Heterophily-guided Unsupervised Graph fraud dEtection approach (HUGE) for unsupervised GFD, which contains two essential components: a heterophily estimation module and an alignment-based fraud detection module. In the heterophily estimation module, we design a novel unsupervised heterophily metric called HALO, which captures the critical graph properties for GFD, enabling its outstanding ability to estimate heterophily with attributes. In the alignment-based fraud detection module, we develop a joint MLP-GNN architecture with ranking loss and asymmetric alignment loss. The ranking loss aligns the predicted fraud score with the relative order of HALO, providing an extra robustness guarantee by comparing heterophily between non-adjacent nodes. Moreover, the asymmetric alignment loss effectively utilizes structural information to alleviate the feature-smooth effects. Extensive experiments on six datasets demonstrate that HUGE consistently outperforms competitors, showcasing its effectiveness and robustness.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (12) , 12443-12451
Open AccessA Label-free Heterophily-guided Approach for Unsupervised Graph Fraud Detection
Graph fraud detection (GFD) has rapidly advanced in protecting online services by identifying malicious fraudsters. Recent supervised GFD research highlights that heterophilic connections between fraudster and user greatly impacts detection performance, where the fraudsters tend to camouflage themselves by building more connections to benign users. Despite their promising performance, their label reliance limits its application in unsupervised scenarios; Additionally, accurately capturing complex and diverse heterophily patterns without labels poses a further challenge. Therefore, we propose a Heterophily-guided Unsupervised Graph fraud dEtection approach (HUGE) for unsupervised GFD, which contains two essential components: a heterophily estimation module and an alignment-based fraud detection module. In the heterophily estimation module, we design a novel unsupervised heterophily metric called HALO, which captures the critical graph properties for GFD, enabling its outstanding ability to estimate heterophily with attributes. In the alignment-based fraud detection module, we develop a joint MLP-GNN architecture with ranking loss and asymmetric alignment loss. The ranking loss aligns the predicted fraud score with the relative order of HALO, providing an extra robustness guarantee by comparing heterophily between non-adjacent nodes. Moreover, the asymmetric alignment loss effectively utilizes structural information to alleviate the feature-smooth effects. Extensive experiments on six datasets demonstrate that HUGE consistently outperforms competitors, showcasing its effectiveness and robustness.
- Top Cited Papers
- 25 February 2025
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 7  (3) , 437-447
Large language models for scientific discovery in molecular property prediction
- 25 February 2025
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 7  (3) , 437-447
Top Cited PapersLarge language models for scientific discovery in molecular property prediction
- 28 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 39  (1) , 64-68
Integrating Graphs With Large Language Models: Methods and Prospects
Large language models (LLMs) such as Generative Pre-trained Transformer 4 have emerged as frontrunners, showcasing unparalleled prowess in diverse applications including answering queries, code generation, and more. Parallelly, graph-structured data, intrinsic data types, are pervasive in real-world scenarios. Merging the capabilities of LLMs with graph-structured data has been a topic of keen interest. This article bifurcates such integrations into two predominant categories. The first leverages LLMs for graph learning, where LLMs can not only augment existing graph algorithms but also stand as prediction models for various graph tasks. Conversely, the second category underscores the pivotal role of graphs in advancing LLMs. Mirroring human cognition, we solve complex tasks by adopting graphs in either reasoning or collaboration. Integrating with such structures can significantly boost the performance of LLMs in various complicated tasks. We also discuss and propose open questions for integrating LLMs with graph-structured data for the future direction of the field.
- 28 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 39  (1) , 64-68
Integrating Graphs With Large Language Models: Methods and Prospects
Large language models (LLMs) such as Generative Pre-trained Transformer 4 have emerged as frontrunners, showcasing unparalleled prowess in diverse applications including answering queries, code generation, and more. Parallelly, graph-structured data, intrinsic data types, are pervasive in real-world scenarios. Merging the capabilities of LLMs with graph-structured data has been a topic of keen interest. This article bifurcates such integrations into two predominant categories. The first leverages LLMs for graph learning, where LLMs can not only augment existing graph algorithms but also stand as prediction models for various graph tasks. Conversely, the second category underscores the pivotal role of graphs in advancing LLMs. Mirroring human cognition, we solve complex tasks by adopting graphs in either reasoning or collaboration. Integrating with such structures can significantly boost the performance of LLMs in various complicated tasks. We also discuss and propose open questions for integrating LLMs with graph-structured data for the future direction of the field.