Tianjin Huang

Hi, I'm an assistant professor in the Department of Computer Science at University of Exeter, and a long-term visiting researcher at Eindhoven University of Technology (TU/e). My research focuses on efficient and reliable machine learning systems, specifically in the following topics:

Model Efficiency
Reliable AI
AI for Science

I am open to collaborating with remote students and visitors (with or without research experience) who are interested in model compression, model editing, robustness, efficient training/tuning of foundation models and large language models, AI for science, etc. ^_^

Call for CSC PhD & Joint-Training (Visiting PhD) Students

Topics: Efficient & Trustworthy Foundation Models, Robust Earth Observation (EO), Agentic AI & Safety, AI for Science, Reliable/Green Training.

What we offer: Co-supervision with partners (e.g., UNC, ELLIS Institute Tübingen), access to Exeter HPC (A100), Isambard-AI (5000 H200) & national resources, supportive publication mentorship.
Funding paths: China Scholarship Council (CSC) full PhD; Exeter–CSC joint program; 6–24 month joint-training/visiting PhD via CSC or home grants.
How to apply: Email your CV, transcripts. Use the subject: “CSC PhD / Joint Training – Your Name”.
Contact: t.huang2@exeter.ac.uk

We welcome emails from prospective students. Feel free to introduce yourself.

News

[Nov. 2025] AAAI 2026 One paper accepted: TimeCAP: A Channel-Aware Pre-Training Framework for Multivariate Time Series Forecasting.
[Oct. 2025] ELLIS Society Joined as an ELLIS Member – grateful to my endorsers, collaborators, and students.
[Sep. 2025] ACM WSDM 2025 One paper accepted: SARC: Sentiment-Augmented Deep Role Clustering for Fake News Detection.
[Sep. 2025] NeurIPS 2025 One paper accepted: REOBench.
[May. 2025] EUSIPCO 2025 Paper accepted: Benchmarking Audio Deepfake Detection Robustness in real-world communication scenarios.
[May. 2025] REOBench Released as a benchmark for evaluating the robustness of Earth observation foundation models (paper).
[May. 2025] MICCAI 2025 One early-accepted paper: LKA.
[May. 2025] ICML 2025 One paper accepted: LIFT.
[Mar. 2025] Expert Systems with Applications One paper accepted: Traffic congestion predictor.
[Mar. 2025] ICLR 2025 SCOPE Workshop Two papers accepted: SPAM and StableSPAM.
[Jan. 2025] ICLR 2025 Three papers accepted: SPAM, Composable Interventions, and Robust Fairness via Confusional Spectral Regularization .
[Dec. 2024] SGAI 2024 Gave an invited talk at the University of Cambridge .
[Dec. 2024] AAAI 2025 One paper accepted: Visual prompting upgrades neural network sparsification.
[Jul. 2024] BMVC 2024 One paper accepted: Are Sparse Neural Networks Better Hard Sample Learners?
[Jun. 2024] NeurIPS 2024 Competition Co-organizing the Edge-Device LLM Challenge .
[Mar. 2024] ICLR 2024 Workshop Paper accepted: Composing Knowledge and Compression Interventions .
[Oct. 2023] Information Fusion Paper accepted: Robust Spatiotemporal GCN.
[Sep. 2023] Complex Networks 2024 Paper accepted: Heterophily-Based GNN for Imbalanced Classification.
[Sep. 2023] NeurIPS 2023 Paper accepted: Dynamic sparsity is channel-level sparsity learner (Channel-DST).
[Jun. 2023] ECML 2023 Paper accepted: Enhancing AT via Refining Optimization Trajectories.
[Apr. 2023] ICML 2023 Paper accepted: Are Large Kernels Better Teachers than Transformers for ConvNets?
[Jan. 2023] ICLR 2023 Oral paper: Sparsity May Cry.
[Nov. 2022] LoG 2022 Best Paper Award: Better GNN by Finding Graph Tickets.
[Nov. 2022] AAAI 2023 Paper accepted: Lottery Pools.
[Jun. 2022] ECML-PKDD 2022 Paper accepted: Hop-count Based Self-Supervised Anomaly Detection.

Selected Publications (full list)

You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets

Tianjin Huang, Tianlong Chen, Meng Fang, Vlado Menkovski, Jiaxu Zhao, Lu Yin, Yulong Pei, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy, Shiwei Liu

LoG 2022 / Paper / Code

Best Paper Award

Are Large Kernels Better Teachers than Transformers for ConvNets?

Tianjin Huang, Lu Yin, Zhenyu Zhang, Li Shen, Meng Fang, Mykola Pechenizkiy, Zhangyang Wang, Shiwei Liu

ICML 2023 / Paper / Code

RT-GCN: Gaussian-based spatiotemporal graph convolutional network for robust traffic prediction

Yutian Liu, Soora Rasouli, Melvin Wong, Tao Feng, Tianjin Huang*

Information Fusion / Paper / Code

Impact Factor: 18.6

Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!

Shiwei Liu, Tianlong Chen, Zhenyu Zhang, Xuxi Chen, Tianjin Huang, Ajay Jaiswal, Zhangyang Wang

ICLR 2023 / Paper / Code

Spotlight Presentation

Dynamic sparsity is channel-level sparsity learner

Lu Yin, Gen Li, Meng Fang, Li Shen, Tianjin Huang, Zhangyang Wang, Vlado Menkovski, Xiaolong Ma, Mykola Pechenizkiy, Shiwei Liu

NeurIPS 2023 / Paper / Code

Enhancing Adversarial Training via Reweighting Optimization Trajectory

Tianjin Huang, Shiwei Liu, Tianlong Chen, Meng Fang, Li Shen, Vlaod Menkovski, Lu Yin, Yulong Pei, Mykola Pechenizkiy

ECML-PKDD 2023 / Paper / Code

Hop-count based self-supervised anomaly detection on attributed networks

Tianjin Huang, Yulong Pei, Vlado Menkovski, Mykola Pechenizkiy

ECML-PKDD 2022 / Paper / Code

Work Experience

University of Exeter

Assistant Professor, June 2024 –

Department of Computer Science

Eindhoven University of Technology

Postdoctoral Fellow, Feb. 2023 – Feb. 2024

Advisor: Professor Mykola Pechenizkiy

Services

Invited Conference Reviewer: NeurIPS, ICLR, ICML, ECCV, ICIP, CPAL, ECML-PKDD, UAI, IDA
Invited Journal Reviewer: IEEE Transactions on Industrial Informatics, Wireless Communications and Mobile Computing, ACM Transactions on Intelligent Systems and Technology