User profiles for Bryan Low
Bryan Kian Hsiang LowAssociate Professor (with tenure), Department of Computer Science, National University of … Verified email at comp.nus.edu.sg Cited by 4746 |
Davinz: Data valuation using deep neural networks at initialization
Recent years have witnessed a surge of interest in developing trustworthy methods to
evaluate the value of data in many real-world applications (eg, collaborative machine learning, …
evaluate the value of data in many real-world applications (eg, collaborative machine learning, …
Variational bayesian unlearning
This paper studies the problem of approximately unlearning a Bayesian model from a small
subset of the training data to be erased. We frame this problem as one of minimizing the …
subset of the training data to be erased. We frame this problem as one of minimizing the …
Federated Bayesian optimization via Thompson sampling
Bayesian optimization (BO) is a prominent approach to optimizing expensive-to-evaluate
black-box functions. The massive computational capability of edge devices such as mobile …
black-box functions. The massive computational capability of edge devices such as mobile …
Gradient driven rewards to guarantee fairness in collaborative machine learning
In collaborative machine learning (CML), multiple agents pool their resources (eg, data)
together for a common learning task. In realistic CML settings where the agents are self-…
together for a common learning task. In realistic CML settings where the agents are self-…
Fault-tolerant federated reinforcement learning with theoretical guarantee
The growing literature of Federated Learning (FL) has recently inspired Federated Reinforcement
Learning (FRL) to encourage multiple agents to federatively build a better decision-…
Learning (FRL) to encourage multiple agents to federatively build a better decision-…
Collaborative machine learning with incentive-aware model rewards
Collaborative machine learning (ML) is an appealing paradigm to build high-quality ML
models by training on the aggregated data from many parties. However, these parties are only …
models by training on the aggregated data from many parties. However, these parties are only …
Validation free and replication robust volume-based data valuation
Data valuation arises as a non-trivial challenge in real-world use cases such as collaborative
machine learning, federated learning, trusted data sharing, data marketplaces. The value …
machine learning, federated learning, trusted data sharing, data marketplaces. The value …
A unifying framework of anytime sparse Gaussian process regression models with stochastic variational inference for big data
This paper presents a novel unifying framework of anytime sparse Gaussian process regression
(SGPR) models that can produce good predictive performance fast and improve their …
(SGPR) models that can produce good predictive performance fast and improve their …
[PDF][PDF] Data Valuation in Machine Learning:" Ingredients", Strategies, and Open Challenges.
Data valuation in machine learning (ML) is an emerging research area that studies the worth
of data in ML. Data valuation is used in collaborative ML to determine a fair compensation …
of data in ML. Data valuation is used in collaborative ML to determine a fair compensation …
NASI: Label-and data-agnostic neural architecture search at initialization
Recent years have witnessed a surging interest in Neural Architecture Search (NAS). Various
algorithms have been proposed to improve the search efficiency and effectiveness of NAS, …
algorithms have been proposed to improve the search efficiency and effectiveness of NAS, …