1 citations · 1 across the 4 of their papers we have counts for
5 papers
Relaxed Efficient Acquisition of Context and Temporal Features
Yunni Qu, Dzung Dinh, Grant King +5
In many biomedical applications, measurements are not freely available at inference time: each laboratory test, imaging modality, or assessment incurs financial cost, time burden,…
Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
Hung-Tien Huang, Dzung Dinh, Junier B. Oliva
Active feature acquisition (AFA) is an instance-adaptive paradigm in which, at inference time, a policy sequentially chooses which features to acquire (at a cost) before predicting…
NOCTA: Non-Greedy Objective Cost-Tradeoff Acquisition for Longitudinal Data
Dzung Dinh, Boqi Chen, Yunni Qu +2
In many critical domains, features are not freely available at inference time: each measurement may come with a cost of time, money, and risk. Longitudinal prediction further compl…
Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching
Yunni Qu, Bhargav Vaduri, Karthikeya Jatoth +6
Machine learning (ML) models are increasingly deployed for virtual screening in drug discovery, where the goal is to identify novel, chemically diverse scaffolds while minimizing e…
The Grand Illusion: The Myth of Software Portability and Implications for ML Progress
Fraser Mince, Dzung Dinh, Jonas Kgomo +2
Pushing the boundaries of machine learning often requires exploring different hardware and software combinations. However, the freedom to experiment across different tooling stacks…