about

I am Ruocheng Guo, a Senior Machine Learning Researcher at ByteDance Research in London, UK. I am actively working on LLM reasoning/alignment, Causal ML and Trustworthy AI. I obtained Ph.D. degree with outstanding Ph.D. student award from Arizona State University advised by Huan Liu.

Research Interests:

• LLMs (Reasoning, Alignment)
• Causal Inference
• Conformal Prediction
• Responsible AI
• Recommendation Systems
• Graph Learning

News

• 11/24 Invited to serve as PC co-chair of the industry track of IEEE DSAA’25
• 11/24 Invited by Dr. Jing Ma to give a guest lecture on conformal causal inference at Case Western Reserve University slides
• 10/24 A paper accepted to NeurIPS’24
• 8/24 Invited to present at 2nd Workshop on Causal Inference and Machine Learning in Practice @ KDD’24

Arxiv Preprints

• Inference-time Stochastic Ranking with Risk Control (rejected by KDD’24 w. novelty/technical quality 5/4)
• Confidence-aware Fine-tuning of Sequential Recommendation Systems via Conformal Prediction
• Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models’ Alignment (presented at SoLaR @ Neurips’23)

Interested in Causality? Please find our papers and algorithm/data repositories.

• Survey Papers
  • Causal Interpretability for Machine Learning–Problems, Methods and Evaluation
  • A Survey of Learning Causality with Data: Problems and Methods
• Repositories
  • Algorithm Repository: Awesome-Causality-Algorithms
  • Data Repository: Awesome-Causality-Data

Recent Accepted Papers

• Causal Inference
  • Learning the Optimal Policy for Balancing Multiple Short-Term and Long-Term Rewards (NeurIPS’24)
  • Conformal Counterfactual Inference under Hidden Confounding (KDD’24)
    • code
  • Debiasing Recommendation by Learning Identifiable Latent Confounders (KDD’23)
    • code
  • Learning for Counterfactual Fairness from Observational Data (KDD’23)
• Fairness
  • Fair Classifiers that Abstain without Harm (ICLR’24)
  • Equal Opportunity of Coverage in Fair Regression (Neurips’23)
    • code
• Graph Learning
  • Tensorized Hypergraph Neural Networks (SDM’24)
  • Federated Knowledge Graph Completion via Latent Embedding Sharing and Tensor Factorization (ICDM’23)
  • Virtual Node Tuning for Few-shot Node Classification (KDD’23)
• Recommendation Systems
  • EASRec: Elastic Architecture Search for Efficient Long-term Sequential Recommender Systems (Recsys’24)
  • Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems (KDD’23 ADS Track)

Experience:

• Senior Machine Learning Researcher, ByteDance Research, June 2022 -
• Assistant Professor, City University of Hong Kong, Aug 2021 - June 2022
• AI Resident, Google [X], Aug 2020 - Dec 2020
• Research Intern, Microsoft Research, May 2020 - Aug 2020
• Research Intern, Etsy, May 2019 - Aug 2019

Students and Interns (and papers co-authored with me)

• Maolin Wang (PhD Student@City University of Hong Kong, Co-supervised w. Xiangyu Zhao and Junhui Wang)
  • WWW’24, SDM’24, ICDM’23
• Chentao Cao (PhD Student@HKBU, Intern@ByteDance Research)
• Zonghao Chen (PhD Student@UCL, Intern@ByteDance Research)
  • KDD’24
• Tongxin Yin (PhD Student@UMich, Intern@ByteDance Research)
  • ICLR’24
• Qing Zhang (PhD Student@HKUST, Intern@ByteDance Research)
  • KDD’23
• Xiaohui Chen (PhD Student@Tufts, Intern@ByteDance)
  • KDD’23
• Sichun Luo (PhD Student@CityU, Intern@ByteDance)
• Xinjian Zhao (Master Student@CityU -> PhD Student@CUHK SZ)
• Jiansheng Li (Master Student@CityU -> PhD Student@CUHK SZ)