Dan Homepage

Nguyen Linh Dan Le

I'm currently a PhD candidate in the Faculty of Engineering and IT at the University of Melbourne under Prof. Andrew Zalesky, Dr. Sidhant Chopra and Dr. Lukas Roell, specialized in brain-computer interfaces and spatiotemporal forecasting of neurodegenerative diseases.

I've had experienced working in AI research at Walter and Eliza Hall Institute of Medical Research as a Data Research Engineer and at Sindy Lab as a Software Engineer in AI detection for academic integrity. Currently, I'm a tutor for Algorithms and Analysis at Royal Melbourne Institute of Technology.

I obtained my Bachelor Degree from The University Of Melbourne in 2024 under Bachelor of Science major in Computer and Software Systems and Master Degree in 2025 from RMIT University.

Research Work Email / University Email / CV / Scholar / Github

News

06/2025 Our paper BrainMAP: Multimodal Graph Learning For Efficient Brain Disease Localization is out for review under IEEE NER 2025
07/2025 Our paper Causal Prompting for Implicit Sentiment Analysis with Large Language Models is out for review under IEEE Transactions on Computational Social Systems
07/2025 Our paper Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-efficient Psychiatric Diagnosis is out for review under AJCAI 2025
08/2025 Our paper BrainMAP: Multimodal Graph Learning For Efficient Brain Disease Localization is ACCEPTED under IEEE NER 2025 in San Diego, USA this December
09/2025 Our paper Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-efficient Psychiatric Diagnosis is ACCEPTED under AJCAI 2025 in Canberra, Australia this December
09/2025 Our paper Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia is out for review under ACM Transactions on Computing for Healthcare
12/2025 Our paper Neuromorphic Dual-Pathway Prompt Learning for Unsupervised Continual Anomaly Detection is out for review under IEEE Transactions on Cognitive and Developmental Systems
01/2026 Our paper Brain PathoGraph Learning is out for review under ACM KDD 2026
01/2026 Our paper Causal Prompting for Implicit Sentiment Analysis with Large Language Models is ACCEPTED under IEEE Transactions on Computational Social Systems
02/2026 Our paper HiBrain: Hierarchical Prototype Learning on Multimodal Brain Graphs for Stage-Aware Biomarker Discovery is out for review under ACM KDD 2026

Research

	BrainMAP: Multimodal Graph Learning For Efficient Brain Disease Localization Nguyen Linh Dan Le, Jing Ren, Ciyuan Peng, Chengyao Xie, Bowen Li, Feng Xia IEEE International Conference on Neural Engineering (NER), 2025 paper \| project page \| A multimodal graph learning framework for efficient brain disease localization, integrating MRI and DTI data to enhance diagnostic accuracy and reduce computational costs.
	Causal Prompting for Implicit Sentiment Analysis with Large Language Models Jing Ren, Wenhao Zhou, Bowen Li, Mujie Liu, Nguyen Linh Dan Le, Jiade Cen, Liping Chen, Ziqi Xu, Xiwei Xu, Xiaodong Li IEEE Transactions on Computational Social Systems paper \| project page \| We propose CAPITAL, a causal prompting framework that incorporates front-door adjustment into CoT reasoning
	Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-efficient Psychiatric Diagnosis Mujie Liu, Chenze Wang, Liping Chen, Nguyen Linh Dan Le, Niharika Tewari, Ting Dang, Jiangang Ma, Feng Xia Australasian Joint Conference on Artificial Intelligence (AJCAI), 2025 paper \| project page \| We propose SAM-BG, a framework designed for low-supervision settings that uses structure-aware augmentation via edge masking to learn robust, biologically meaningful brain graph representations from large-scale, unlabeled fMRI data.
	Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia Niharika Tewari, Nguyen Linh Dan Le, Mujie Liu, Jing Ren , Ziqi Xu, Tabinda Sarwar, Veeky Baths, Feng Xia ACM Transactions on Computing for Healthcare, 2025 paper This paper presents the first comprehensive review dedicated to XGNNs in dementia research. A taxonomy of explainability methods tailored for dementia-related tasks is introduced, alongside comparisons of existing models in clinical scenarios. We also highlight challenges such as limited generalizability, underexplored domains, and the integration of Large Language Models (LLMs) for early detection.
	Brain PathoGraph Learning Ciyuan Peng, Nguyen Linh Dan Le, Shan Jin, Dexuan Ding, Shuo Yu, Feng Xia A Conference*, 2026 paper \| project page \| We proposed BrainPoG, a lightweight graph learning model that reduce disease-irrelevant nodes and noise features to enhance model efficiency and predictive accuracy

Academic Services

Conference Reviewer: NeurIPS (2025)
Conference Reviewer: ACM KDD (2026)

Honors and Awards

IEEE NER Student Grant: Nov 2025
Melbourne Research Scholarship: February 2026

Teaching

Algorithms and Analysis (COSC2123 & COSC3119): RMIT University

template adapted from this awesome website