About me

I am a Ph.D. student in ECE at Purdue University under the supervision of Prof. Jing Gao. Before coming to Purdue, I spent two wonderful years at University of Michigan to acquire my MS degree in Statistics. Prior to that, I got my BS degree from Xiamen University.

I am broadly interested in trustworthy machine learning with a special focus on comprehending and enhancing the effectiveness of trustworthy machine learning methods in adverse scenarios. Some topics I explored recently include supervision-efficient fair machine learning and fair machine learning security.

Education

2021 - 2026 (Expected), Ph.D. in Electrical and Computer Engineering, Purdue University

2019 - 2021, M.S. in Applied Statistics, University of Michigan

2013 - 2017, B.S. in Statistics, School of Economics, Xiamen University

Publications

Conference Publications

[NeurIPS’24] Zeyu Zhou, Tianci Liu, Ruqi Bai, Jing Gao, Murat Kocaoglu, David Inouye, “Counterfactual Fairness by Combining Factual and Counterfactual Predictions.” The 38th Annual Conference on Neural Information Processing Systems, Vancouver, Canada, Dec 2024.

[NeurIPS’24] Feijie Wu, Xingchen Wang, Yaqing Wang, Tianci Liu, Lu Su, Jing Gao, “FIARSE: Model-Heterogeneity Federated Learning via Importance-Aware Submodel Extraction.” The 38th Annual Conference on Neural Information Processing Systems, Vancouver, Canada, Dec 2024.

[EMNLP’24] Haoyu Wang, Tianci Liu, Ruirui Li, Monica Cheng, Tuo Zhao, Jing Gao, “RoseLoRA: Row and Column-wise Sparse Low-Rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning.” The 2024 Conference on Empirical Methods in Natural Language Processing, Miami, Florida, Nov 2024.
(Oral)

[SenSys’24] Qiming Cao, Hongfei Xue, Tianci Liu, Xingchen Wang, Haoyu Wang, Xincheng Zhang, Lu Su, “mmCLIP: Boosting mmWave-based Zero-shot HAR via Signal-Text Alignment.” The 22nd ACM Conference on Embedded Networked Sensor System, Hangzhou, China, Nov 2024.

[SenSys’24] Xingchen Wang, Haoyu Wang, Feijie Wu, Tianci Liu, Qiming Cao, Lu Su, “Towards Efficient Heterogeneous Multi-Modal Federated Learning with Hierarchical Knowledge Disentanglement.” The 22nd ACM Conference on Embedded Networked Sensor System, Hangzhou, China, Nov 2024.

[ICML’24] Tianci Liu, Haoyu Wang, Shiyang Wang, Yu Cheng, Jing Gao, “LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models.” The 41st International Conference on Machine Learning, Vienna, Austria, Jul 2024.
(Spotlight)

[ICLR’24] Tianci Liu, Haoyu Wang, Feijie Wu, Hengtong Zhang, Pan Li, Lu Su, Jing Gao, “Towards Poisoning Fair Representations.” The 12th International Conference on Learning Representations, Vienna, Austria, May 2024.

[EMNLP’23] Haoyu Wang, Yaqing Wang, Tianci Liu, Tuo Zhao, Jing Gao, “HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference.” Findings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, Dec 2023.

[ICML’23] Tianci Liu\(^\ast\), Tong Yang\(^\ast\), Quan Zhang, Qi Lei, “Optimization for Amortized Inverse Problems.” The 40th International Conference on Machine Learning, Honolulu, Hawaii, Jul 2023.
(Equal contribution)

[AAAI’23] Tianci Liu, Haoyu Wang, Yaqing Wang, Xiaoqian Wang, Lu Su, Jing Gao, “SimFair: A Unified Framework for Fairness-Aware Multi-Label Classification.” The 37th AAAI Conference on Artificial Intelligence, Washington D.C., Feb 2023.
(Distinguished Paper Award)

[DeepInverse@NeurIPS’21] Tianci Liu, Quan Zhang, Qi Lei, “PANOM: Automatic Hyper-parameter Tuning for Inverse Problems.” NeurIPS Workshop on Deep Learning and Inverse Problems, Virtual, Dec 2021.

[BDL@NeurIPS’21] Tianci Liu, Jeffrey Regier, “An Empirical Comparison of GANs and Normalizing Flows for Density Estimation.” NeurIPS Workshop on Bayesian Deep Learning, Virtual, Dec 2021.

Journal Publications

Daiwei Zhang, Tianci Liu, Jian Kang (2023) “Density Regression and Uncertainty Quantification with Bayesian Deep Noise Neural Networks.” Stat, 12(1), e604.

Laura Zichi, Tianci Liu, Elizabeth Drueke, Liuyan Zhao, and Gongjun Xu (2023) “Physically informed machine-learning algorithms for the identification of two-dimensional atomic crystals.” Scientific Reports 13(1): 6143.

Tianci Liu, Chun Wang, Gongjun Xu (2022) “Estimating three- and four-parameter MIRT models with importance-weighted sampling enhanced variational auto-encoder.” Frontiers in Psychology, 13:935419.