
Bibek Paudel
Postdoctoral Research Fellow, Sean N Parker Center for Allergy & Asthma Research
Bio
I am a Postdoctoral Research Fellow at the Department of Biomedical Data Science. My research focuses on developing machine learning and statistical models to solve problems that are inter-disciplinary in nature, including those from the biomedical, ecological, and socio-political sciences. I received my Ph.D. in Computer Science from University of Zurich, Switzerland in 2019, where I developed new algorithms to improve recommendation diversity and algorithmic fairness. I used graph theory, deep learning, and latent-factor models to build documents representations, explainable knowledge base embeddings, and personalization systems. At Stanford, I am building new machine learning models for personalized medicine by combining biological domain knowledge and large heterogeneous datasets. My research spans both ends of the biomedical data spectrum: from single-cell observations to population health data. I am particularly interested in examining the disparate health impacts of environmental factors on vulnerable and minority populations and in understanding how these findings can guide policy interventions.
All Publications
-
Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
ASSOC COMPUTING MACHINERY. 2019: 2366–77
View details for DOI 10.1145/3308558.3313612
View details for Web of Science ID 000483508402040
- Loss Aversion in Recommender Systems: Utilizing Negative User Preference to Improve Recommendation Quality The First International Workshop on Context-Aware Recommendation Systems with Big Data Analytics (CARS-BDA), co-organized with the 12th ACM International Conference on Web Search and Data Mining 2019
-
Interaction Embeddings for Prediction and Explanation in Knowledge Graphs
ASSOC COMPUTING MACHINERY. 2019: 96–104
View details for DOI 10.1145/3289600.3291014
View details for Web of Science ID 000482120400016
- Cross-Cutting Political Awareness through Diverse News Recommendations European Symposium Series on Societal Challenges in Computational Social Science EuroCSS. 2019
- Bringing Diversity in News Recommender Algorithms ECREA 2018 - pre-conference workshop on Information, Diversity and Media Pluralism in the Age of Algorithms 2018
-
Aligning Knowledge Base and Document Embedding Models Using Regularized Multi-Task Learning
SPRINGER INTERNATIONAL PUBLISHING AG. 2018: 21–37
View details for DOI 10.1007/978-3-030-00671-6_2
View details for Web of Science ID 000476939700002
-
Updatable, Accurate, Diverse, and Scalable Recommendations for Interactive Applications
ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS
2017; 7 (1)
View details for DOI 10.1145/2955101
View details for Web of Science ID 000399087600001
-
Fewer Flops at the Top: Accuracy, Diversity, and Regularization in Two-Class Collaborative Filtering
ASSOC COMPUTING MACHINERY. 2017: 215–23
View details for DOI 10.1145/3109859.3109916
View details for Web of Science ID 000426967000033
-
Random Walk TripleRush: Asynchronous Graph Querying and Sampling
ASSOC COMPUTING MACHINERY. 2015: 1034–44
View details for DOI 10.1145/2736277.2741687
View details for Web of Science ID 000467281500096
-
Blockbusters and Wallflowers: Accurate, Diverse, and Scalable Recommendations with Random Walks
RecSys '15: Proceedings of the 9th ACM Conference on Recommender Systems
ASSOC COMPUTING MACHINERY.. 2015: 163–170
View details for DOI 10.1145/2792838.2800180