Welcome to the personal page of Ben Liao. This outdated page is no longer maintained.
Research interests
Computing: neural network (transformers, diffusion model, RNN, CNN, GNN), algorithm design, efficiency & complexity
Modeling: (machine learnt) language & vision, physics & science
Mathematics: operator algebras (functional analysis), geometry of groups/graphs, probability theory.
Academic services
Reviewer of NeurIPS, ICML, ICLR
Reviewer of J. Funct. Anal., Israel J. Math., JTA
Education
Ph.D., 2010-2014,
Université de Paris (Diderot), France
(supervised by V. Lafforgue and G. Skandalis)
Bachelor in mathematics, 2006-2010,
University of Science and Technology of China
Articles in machine learning
Weizhao Li, Junsheng Kong, Ben Liao, Yi Cai
Mitigating Contradictions in Dialogue Based on Contrastive Learning.
60th Annual Meeting of the Association for Computational Linguistics (ACL 2022 findings). [link]
Junsheng Kong, Weizhao Li, Zeyi Liu, Ben Liao (corresponding author), Jiezhong Qiu, Chang-Yu Hsieh, Yi Cai, Shengyu Zhang.
Fast Extraction of Word Embedding from Q-contexts.
Proceedings of the 30th ACM International Conference on Information & Knowledge Management (CIKM 2021). [spotlight presentation][link][arXiv]
Jiezhong Qiu, Chi Wang, Ben Liao, Richard Peng, Jie Tang.
Concentration Bounds for Co-occurrence Matrices of Markov Chains.
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020) [link][arXiv]
Pengfei Chen, Benben Liao, Guangyong Chen, Shengyu Zhang
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels.
Proceedings of the 36th International Conference on Machine Learning (ICML 2019), PMLR 97:1062-1070, 2019. [link][arXiv]
G. Chen, C-Y Hsieh, C-K Lee, B. Liao, et al.
AlChemy: A Quantum Chemistry Dataset for Benchmarking AI Models.
In International Conference on Learning Representations (ICLR 2019) workshop, 2019. [link]
Weiwen Liu, Feng Liu, Ruiming Tang, Ben Liao, Guangyong Chen, Pheng Ann Heng
Balancing between Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning.
In The 24th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2020). [link]
Yitong Meng, Xinyan Dai, Xiao Yan, James Cheng, Weiwen Liu, Benben Liao, et al.
PMD: An Optimal Transportation-based User Distance for Recommender Systems.
In European Conference on Information Retrieval (ECIR 2020). [arXiv][link]
Yaodong Yang, Jianye Hao, Ben Liao, et al.
Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning. [arXiv]
Guangyong Chen, Pengfei Chen, Yujun Shi, Chang-Yu Hsieh, Benben Liao (corresponding author), Shengyu Zhang.
Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks. [arXiv]
ML for science
RetroPrime: A Diverse, Plausible and Transformer-based Method for Single-Step Retrosynthesis Predictions
X Wang, Y Li, J Qiu, G Chen, H Liu, B Liao (corresponding author), CY Hsieh, X Yao
Chemical Engineering Journal
Hyperbolic relational graph convolution networks plus: a simple but highly efficient QSAR-modeling method
Z Wu, D Jiang, CY Hsieh, G Chen, B Liao, D Cao, T Hou
Briefings in Bioinformatics
Articles in mathematics
Noncommutative maximal ergodic inequalities associated with doubling conditions,
with Guixiang Hong and Simeng Wang,
Duke Mathematical Journal 170 (2) 205 - 246, 1 February 2021. https://doi.org/10.1215/00127094-2020-0034 [journal][arXiv]
K-theory of group Banach algebras and Banach property RD,
with Guoliang Yu, to appear in
Compositio Mathematica. [arXiv]
About the obstacle to prove the Baum Connes conjecture without coefficient for a non-cocompact lattice in Sp4 in a local field.
Journal of Noncommutative Geometry, 10 (2016), 1243-1268. doi: 10.4171/JNCG/259. [journal][arXiv]
Strong Banach property (T) for simple algebraic groups of higher rank.
Journal of Topology and Analysis, 06, 75 (2014) DOI: 10.1142/S1793525314500010. [journal][arXiv]
Approximation properties for p-adic symplectic groups and lattices, submitted, [arXiv].
Geometric strong property (T), with Mikael de la Salle and Maria Paula Gomez Aparicio, in preparation
Technical reports
Regret analysis in reinforcement learning and Banach space exponential inequalities
liao ta hotmail.co.uk
(replace 'ta' by '@')