I am a PhD student in Machine Learning Department at Carnegie Mellon University, advised by Prof. Kun Zhang (CMU-CLeaR Group). Before that, I was an undergraduate student in Data Mining Group in Computer Science at University of Illinois at Urbana-Champaign, where I was fortunate to be advised by Prof. Jiawei Han.

Research

My research focuses on Machine Learning and Causality, with an emphasis on automated knowledge construction using provable (causal) representations. I have developed causal representation learning methods for sequential data, including time series, text, and video (NeurIPS’23, ICML’24, NeurIPS’24, arXiv’24a, arXiv’24b). These methods provably recover data generation processes and construct causal representations.

I am currently interested in leveraging such causal lens to study how foundation models perform inference and reasoning, with the goal of understanding and controlling their latent cognitive processes in a principled way.

Contact

The easiest way to reach me is email. My address is xiangchensong [at] cmu [dot] edu.

What’s New

• [Sep. 2024] One paper “Causal Temporal Representation Learning with Nonstationary Sparse Transition” has been accepted to The Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS’2024)!!
• [May. 2024] One paper “CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process” has been accepted to The Forty-first International Conference on Machine Learning (ICML’2024)!!
• [Jan. 2024] One paper “A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables” has been accepted to The Twelfth International Conference on Learning Representations (ICLR’2024)!!
• [Sep. 2023] One paper “Temporally Disentangled Representation Learning under Unknown Nonstationarity” has been accepted to The Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS’2023)!!
• [Jan. 2023] One paper “Prompt Learning with Optimal Transport for Vision-Language Models” has been accepted to The International Conference on Learning Representations (ICLR’2023)!!
• [Nov. 2022] One paper “Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders” has been accepted to The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI’2023)!!
• [Jan. 2022] One paper “Creating Training Sets via Weak Indirect Supervision” has been accepted to The International Conference on Learning Representations (ICLR’2022)!!
• [Jan. 2022] One paper “TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations” has been accepted to The Web Conference (WWW’2022)!!
• [Nov. 2021] One paper “Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Recommendation” has been accepted to 38th IEEE International Conference on Data Engineering (ICDE’2022)!!
• [Nov. 2021] Serve as Workflow Chair for UAI 2022.
• [Nov. 2021] Our python package for causal discovery causal-learn was released. Any feedback is welcome.
• [Oct. 2021] One paper “Learning Multi-granularity Consecutive User Intent Unit for Session-based Recommendation” has been accepted to The Fifteenth International Conference on Web Search and Data Mining (WSDM’2022)!!
• [Aug. 2021] One paper “ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-guided Distant Supervision” has been accepted to Empirical Methods in Natural Language Processing (EMNLP’2021)!!
• [Mar. 2021] One paper “COVID‑19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation” has been accepted to System Demonstration of 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL’2021)!!
• [Mar. 2021] One paper “Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion” has been accepted to The Workshop on Self-Supervised Learning for the Web (SSL@WWW’2021)!!
• [Feb. 2021] I am honored to receive Conference Travel Grant sponsored by Office of Undergraduate Research (OUR) at the University of Illinois.
• [Feb. 2021] I will join Machine Learning Department at Carnegie Mellon University as a PhD student starting from Fall 2021.
• [Jan. 2021] I am honored to receive WSDM 2021 Student Travel Award sponsored by SIGIR.
• [Dec. 2020] I am honored to be selected as one of the honorable mention for the 2020-2021 CRA Outstanding Undergraduate Researchers Award.
• [Dec. 2020] One paper “Taxonomy Completion via Triplet Matching Network” has been accepted to The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI’2021)!!
• [Oct. 2020] One paper “Fine-Grained Named Entity Recognition with Distant Supervision in COVID-19 Literature” has been accepted into IEEE International Conference on Bioinformatics and Biomedicine 2020 (IEEE BIBM’2020)!!
• [Oct. 2020] One paper “BiTe-GCN: A New GCN Architecture via Bidirectional Convolution of Topology and Features on Text-Rich Networks” has been accepted into The 14th ACM International Conference on Web Search and Data Mining (WSDM’2021)!!
• [Oct. 2020] I am honored to be selected as one of the department’s nominations for the 2020-2021 CRA Outstanding Undergraduate Researchers Award.
• [May. 2020] One paper “Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision” has been accepted as oral and poster into The 28th International Conference on Intelligent Systems for Molecular Biology (ISMB’2020)!!
• [Mar. 2020] I am honored to receive John R. Pasta Outstanding Undergraduate Award from Department of Computer Science, University of Illinois at Urbana-Champaign.