-
The Hong Kong University of Science and Technology
- Hong Kong
-
08:14
(UTC -12:00) - http://data-designer.github.io/
Highlights
Starred repositories
This is the implementation of the paper: Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation.
Source code of the paper titled "Unity in Diversity: Collaborative Pre-training Across Multimodal Medical Sources".
A Bayesian Neural Network with a horseshoe prior for improved interpretability
ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context (AAAI-2020)
Toolkit for evaluating and monitoring AI models in clinical settings
[NeurIPS'24] Knowledge Graph Fine-Tuning with Open-World Knowledge
Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval
Accepted as a short paper at CIKM 2024.
The repository for WWW'24 short paper "Proactive Recommendation with Iterative Preference Guidance".
Source code for a comprehensive analysis of MTL over EHR timeseries data.
Codes for "CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation"
Quantifying biases in BERT embeddings pretrained on MIMIC-III clinical notes
[WSDM 2024 Oral] This is our Pytorch implementation for the paper: "Intent Contrastive Learning with Cross Subsequences for Sequential Recommendation".
[AAAI 2022] DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction
This repository contains my research work on building the state of the art next basket recommendations using techniques such as Autoencoders, TF-IDF, Attention based BI-LSTM and Transformer Networks
An implementation of (Induced) Set Attention Block, from the Set Transformers paper