Kun Kuang
ABSTRACT
In causality-based trustworthy machine learning, finding mechanisms from data-driven correlation analysis to causal inference and constructing a machine learning framework from correlation-driven to causality-driven are two significant challenges. To address these challenges, we propose a series of innovations, including data-driven causal inference mechanisms, causality-inspired interpretable and stable learning frameworks, causality-based generalizable graph neural network learning frameworks, and other fundamental theories and key technologies. To further support the development of the field, we make the corresponding codes and resources public in the open-source community, including the big data causal inference framework based on instrumental variables (https://github.com/causal-machine-learning-lab/mliv) and the large-scale graph neural network computing and edge-cloud collaborative learning platform (https://github.com/luoxi-model/luoxi_models).
- Zhengyu Chen, Teng Xiao, and Kun Kuang. 2022. BA-GNN: On Learning Bias-Aware Graph Neural Network. In 38th IEEE International Conference on Data Engineering, ICDE 2022, Kuala Lumpur, Malaysia, May 9-12, 2022. IEEE, 3012–3024. https://doi.org/10.1109/ICDE53745.2022.00271Google Scholar
- Kun Kuang, Peng Cui, Susan Athey, Ruoxuan Xiong, and Bo Li. 2018. Stable Prediction across Unknown Environments. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2018, London, UK, August 19-23, 2018, Yike Guo and Faisal Farooq (Eds.). ACM, 1617–1626. https://doi.org/10.1145/3219819.3220082Google ScholarDigital Library
- Kun Kuang, Peng Cui, Hao Zou, Bo Li, Jianrong Tao, Fei Wu, and Shiqiang Yang. 2022. Data-Driven Variable Decomposition for Treatment Effect Estimation. IEEE Trans. Knowl. Data Eng. 34, 5 (2022), 2120–2134. https://doi.org/10.1109/TKDE.2020.3006898Google ScholarCross Ref
- Kun Kuang, Haotian Wang, Yue Liu, Ruoxuan Xiong, Runze Wu, Weiming Lu, Yueting Zhuang, Fei Wu, Peng Cui, and Bo Li. 2023. Stable Prediction With Leveraging Seed Variable. IEEE Trans. Knowl. Data Eng. 35, 6 (2023), 6392–6404. https://doi.org/10.1109/TKDE.2022.3169333Google ScholarDigital Library
- Kun Kuang, Ruoxuan Xiong, Peng Cui, Susan Athey, and Bo Li. 2020. Stable Prediction with Model Misspecification and Agnostic Distribution Shift. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020. AAAI Press, 4485–4492. https://ojs.aaai.org/index.php/AAAI/article/view/5876Google ScholarCross Ref
- Anpeng Wu, Kun Kuang, Bo Li, and Fei Wu. 2022. Instrumental Variable Regression with Confounder Balancing. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA(Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu, and Sivan Sabato (Eds.). PMLR, 24056–24075. https://proceedings.mlr.press/v162/wu22e.htmlGoogle Scholar
- Shengyu Zhang, Fuli Feng, Kun Kuang, Wenqiao Zhang, Zhou Zhao, Hongxia Yang, Tat-Seng Chua, and Fei Wu. 2023. Personalized Latent Structure Learning for Recommendation. IEEE Trans. Pattern Anal. Mach. Intell. 45, 8 (2023), 10285–10299. https://doi.org/10.1109/TPAMI.2023.3247563Google ScholarDigital Library
Index Terms
- Causal Inspired Trustworthy Machine Learning
Recommendations
Causal Learning with Occam’s Razor
AbstractOccam’s razor directs us to adopt the simplest hypothesis consistent with the evidence. Learning theory provides a precise definition of the inductive simplicity of a hypothesis for a given learning problem. This definition specifies a learning ...
Machine Learning: The State of the Art
The two fundamental problems in machine learning (ML) are statistical analysis and algorithm design. The former tells us the principles of the mathematical models that we establish from the observation data. The latter defines the conditions on which ...
Comments