77 citations · 584 across the 84 of their papers we have counts for
12 papers · 2 filters
Data value estimation on private gradients
Zijian Zhou, Xinyi Xu, Daniela Rus +1
For gradient-based machine learning (ML) methods commonly adopted in practice such as stochastic gradient descent, the de facto differential privacy (DP) technique is perturbing th…
Data Distribution Valuation
Xinyi Xu, Shuaiqi Wang, Chuan-Sheng Foo +2
Data valuation is a class of techniques for quantitatively assessing the value of data for applications like pricing in data marketplaces. Existing data valuation methods define a…
Global-to-Local Support Spectrums for Language Model Explainability
Lucas Agussurja, Xinyang Lu, Bryan Kian Hsiang Low
Existing sample-based methods, like influence functions and representer points, measure the importance of a training point by approximating the effect of its removal from training.…
Neural Dueling Bandits: Preference-Based Optimization with Human Feedback
Arun Verma, Zhongxiang Dai, Xiaoqiang Lin +2
Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback ov…
Prompting the Unknown: Understanding Response Uncertainty in Large Language Models
Ze Yu Zhang, Arun Verma, Finale Doshi-Velez +1
Large language models (LLMs) are widely used in decision-making across diverse domains. Ensuring the generation of safe and reliable responses is critical for the effective deploym…
Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
Jingtan Wang, Xiaoqiang Lin, Rui Qiao +2
The increasing complexity of foundational models underscores the necessity for explainability, particularly for fine-tuning, the most widely used training method for adapting model…
Prompt Optimization with Human Feedback
Xiaoqiang Lin, Zhongxiang Dai, Arun Verma +3
Large language models (LLMs) have demonstrated remarkable performances in various tasks. However, the performance of LLMs heavily depends on the input prompt, which has given rise…
PINNACLE: PINN Adaptive ColLocation and Experimental points selection
Gregory Kang Ruey Lau, Apivich Hemachandra, See-Kiong Ng +1
Physics-Informed Neural Networks (PINNs), which incorporate PDEs as soft constraints, train with a composite loss function that contains multiple training point types: different ty…
Incentives in Private Collaborative Machine Learning
Rachael Hwee Ling Sim, Yehong Zhang, Trong Nghia Hoang +3
Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation. Existing data valuation methods fairly value and rew…
Robustifying and Boosting Training-Free Neural Architecture Search
Zhenfeng He, Yao Shu, Zhongxiang Dai +1
Neural architecture search (NAS) has become a key component of AutoML and a standard tool to automate the design of deep neural networks. Recently, training-free NAS as an emerging…
DeRDaVa: Deletion-Robust Data Valuation for Machine Learning
Xiao Tian, Rachael Hwee Ling Sim, Jue Fan +1
Data valuation is concerned with determining a fair valuation of data from data sources to compensate them or to identify training examples that are the most or least useful for pr…
Understanding Domain Generalization: A Noise Robustness Perspective
Rui Qiao, Bryan Kian Hsiang Low
Despite the rapid development of machine learning algorithms for domain generalization (DG), there is no clear empirical evidence that the existing DG algorithms outperform the cla…