Haiping Lu

Professor of Machine Learning, Head of AI Research Engineering, and Turing Academic Lead

The University of Sheffield

I am a Professor of Machine Learning and AI Strategy Lead at the School of Computer Science, Founding Head of AI Research Engineering at the Centre for Machine Intelligence, and the Turing Academic Lead at the University of Sheffield. I am the lead organiser and founder of the Alan Turing Institute’s interest group on Meta-learning for multimodal data (welcome to sign up and join) and the annual Multimodal AI Workshop and Research Sprint (welcome to subscribe to our Multimodal AI Community mailing list). I lead the development of a course on An Introduction to Transparent Machine Learning, part of the Alan Turing Institute’s online learning courses in responsible AI.

My research focuses on developing translational AI technologies for better analysing multimodal data in healthcare and beyond, particularly multidimensional data and heterogeneous graphs in bioinformatics and medical imaging. I lead the development of the PyKale library to provide more accessible machine learning from multiple sources for interdisciplinary research, officially part of the PyTorch ecosystem.

I serve as an Associate Editor of IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Cognitive and Developmental Systems, and the World Scientific Annual Review of Artificial Intelligence. I served as an area chair of IJCAI2021, and a senior program committee member of IJCAI and AAAI since 2018. I was a recipient of a Turing Network Development Award, an Amazon Research Award, an AAAI Outstanding PC Member Award, a Hong Kong Research Grants Council Early Career Award, an IEEE CIS Outstanding PhD Dissertation Award, and a joint recipient of a Wellcome Trust Innovator Award and an NIHR AI in Health and Care Award. I am a Senior Member of IEEE.

Three of my MSc dissertation students received the Fretwell-Downing Prize for the best MSc Dissertation in their respective years (P. Bai in 2017, H. Xu in 2019, and M. N. I. Suvon in 2022). See the bottom for the whereabouts of my past team members.

PhD enquiries: Email me ONE PDF including CV, a statement on why and your source of funding, 1-3 papers, and transcripts before applying. Also check the English language requirements.

Research

Adventure and voyage of discovery

We aim to develop translational AI technologies for better analysing multimodal data in healthcare and beyond, particularly multidimensional data and heterogeneous graphs in bioinformatics and medical imaging. More specifically, we build knowledge-aware machine learning tools for learning useful features from multidimensional data and analysing complex relationships in graphs/networks via tensor-based, graph-based, and related methods.

See selected research projects below, which can be filtered by the tags. Explore a list of all projects »

PyKale: an ML Library in PyTorch Ecosystem

Make machine learning more accessible to interdisciplinary research by bridging gaps between data, software, and end users

Uncertainty Est. for Landmark Localisation

Quantify the uncertainty in automatic anatomical landmark localisation

Low-Bias Evaluation of Drug-Target Interaction

Hierarchical clustering split for low-bias evaluation of drug-target interaction prediction

Human-In-The-Loop DL for Cardiac CT/MRI

Interactively trained ‘human-in-the-loop’ deep learning to improve cardiac CT/MRI assessment for accurate therapy response and mortality prediction

Mixed-order Spectral Clustering for Networks

Model both second-order and third-order structures simultaneously for complex networks

Multisite Brain fMRI Classification

Multi-site autism classification based on site-dependence minimisation and second-order functional connectivity

Interpretable ML for Cardiac MRI

Interpretable machine learning to improve prognostic and treatment response assessment on cardiac MRI

Learnable GCN Aggregator

A feature-importance-aware and robust aggregator for graph convolutional networks (GCNs)

Learn via Tensor Model

Learn low-dimensional representations of high-dimensional data from their natural tensors

Selected Papers

List of publications up to Feb'22»

Profiles: Google Scholar, ResearcherID, ScopusAuthorID, Semantic Scholar.

See an up-to-date full list of publications in my CV (from page 2). Publications after Feb 2022 are not updated on this website due to lack of time.

See papers selected in 2021 below. Explore publications up to Feb 2022 > to filter/search.

Yan Ge, Pan Peng, Haiping Lu (2021). Mixed-order spectral clustering for complex networks. Pattern Recognition.

Cite Link PDF Code

Andrew Swift, Haiping Lu, Johanna Uthoff, Pankaj Garg, Marcella Cogliano, Jonathan Taylor, Peter Metherall, Shuo Zhou, Christopher S Johns, Samer Alabed, Robin Condliffe, Allan Lawrie, Jim Wild, David Kiely (2021). A machine learning cardiac magnetic resonance approach to extract disease features and automate pulmonary arterial hypertension diagnosis. European Heart Journal-Cardiovascular Imaging.

Cite Link PDF Code Data Colab demo

Li Zhang, Haiping Lu (2020). A feature-importance-aware and robust aggregator for GCN. ACM International Conference on Information and Knowledge Management (CIKM).

Cite Link PDF PyTorch Code TensorFlow Code

Shuo Zhou, Wenwen Li, Christopher Cox, Haiping Lu (2020). Side information dependence as a regularizer for analyzing human brain conditions across cognitive experiments. AAAI Conference on Artificial Intelligence (AAAI).

Cite Link PDF Code

Peizhen Bai, Yan Ge, Fangling Liu, Haiping Lu (2019). Joint interaction with context operation for collaborative filtering. Pattern Recognition.

Cite Link PDF

Teaching

Learn to teach, teach to learn

I lead the development of a course on An Introduction to Transparent Machine Learning, part of the Alan Turing Institute’s online learning courses in responsible AI.

At the University of Sheffield, I am teaching two modules below, with teaching materials available on GitHub via links below and video lectures on YouTube. See my CV for my previous teaching experience.

Spring 2017-2023: COM6012 Scalable Machine Learning
Fall 2018-2021: COM4509/6509 Machine Learning and Adaptive Intelligence

Code & Data

Open sources accelerate advances

PyKale We develop the PyKale library in the PyTorch ecosystem to make machine learning more accessible to interdisciplinary research by bridging gaps between data, software, and end users.

The Matlab code of algorithms and related data from my earlier works.

Remurs (Regularized Multilinear Regression and Selection): Remurs Version 1.0: code, data, and paper (2.85MB)
UMLDA (Uncorrelated Multilinear Discriminant Analysis): UMLDA Version 1.1: code, data, and paper (19.73MB)
RCSP (Regularized Common Spatial Pattern): RCSP Version 1.0: code and paper (2.19MB)
UMPCA (Uncorrelated Multilinear Principal Component Analysis): UMPCA Version 1.0: code, data, and paper (7.87MB)
MPCA (Multilinear Principal Component Analysis): MPCA Version 1.3 package: code, data, samples, and paper (5.18MB)
Gait data: 128x88x20(21.2M); 64x44x20(9.9M); 32x22x10(3.2M)
Binary Image Watermarking/Data Hiding: Binary Image Watermarking/Data Hiding: Data, Algorithms, and Distortion Measure (3.7MB)

The KALE Group

PhD enquiries: Email me ONE PDF including CV, a statement on why and your source of funding, 1-3 papers, and transcripts before applying. Also check the English language requirements.

KALE stands for Knowledge-Aware machine LEarning. We aim to leverage heterogeneous data sources and domain expert knowledge to transform real-world applications with AI and machine learning. KALE also symbolises our Green Machine Learning principles and health theme. See our latest group photo in June 2023 below or older group photos in Dec 2021, Jan 2020 and Oct 2019. Explore brief profiles of current research staff/students, collaborators, and alumni under the group photo.