11 citations · 40 across the 18 of their papers we have counts for
13 papers · 1 filter
MoPLEx: Estimating Plackett-Luce Mixture Models for Multi-Objective Alignment
Dongyue Li, Ziniu Zhang, Lu Wang +1
We study learning a mixture of Plackett-Luce models from multi-way ranking responses from annotators that may represent heterogeneous underlying preferences. This problem has m…
WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points
Dongyue Li, Zechun Liu, Kai Yi +6
Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is…
Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
Dongyue Li, Zhenshuo Zhang, Minxuan Duan +2
Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning abilities, designed for graph neural…
Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation
Ziniu Zhang, Zhenshuo Zhang, Dongyue Li +3
This paper introduces an algorithm to select demonstration examples for in-context learning of a query set. Given a set of examples, how can we quickly select out of to…
Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets
Dongyue Li, Ziniu Zhang, Lu Wang +1
This paper develops an ensemble method for fine-tuning a language model to multiple datasets. Existing methods, such as quantized LoRA (QLoRA), are efficient when adapting to a sin…
Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity
Dongyue Li, Aneesh Sharma, Hongyang R. Zhang
Multitask learning is a widely used paradigm for training models on diverse tasks, with applications ranging from graph neural networks to language model fine-tuning. Since tasks m…
Learning Tree-Structured Composition of Data Augmentation
Dongyue Li, Kailai Chen, Predrag Radivojac +1
Data augmentation is widely used for training a neural network given little labeled data. A common practice of augmentation training is applying a composition of multiple transform…
Boosting Multitask Learning on Graphs through Higher-Order Task Affinities
Dongyue Li, Haotian Ju, Aneesh Sharma +1
Predicting node labels on a given graph is a widely studied problem with many applications, including community detection and molecular graph prediction. This paper considers predi…
Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach
Hongyang R. Zhang, Dongyue Li, Haotian Ju
The training of over-parameterized neural networks has received much study in recent literature. An important consideration is the regularization of over-parameterized networks due…
Identification of Negative Transfers in Multitask Learning Using Surrogate Models
Dongyue Li, Huy L. Nguyen, Hongyang R. Zhang
Multitask learning is widely used in practice to train a low-resource target task by augmenting it with multiple related source tasks. Yet, naively combining all the source tasks w…
Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
Haotian Ju, Dongyue Li, Aneesh Sharma +1
Graph neural networks are widely used tools for graph prediction tasks. Motivated by their empirical performance, prior works have developed generalization bounds for graph neural…
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
Haotian Ju, Dongyue Li, Hongyang R. Zhang
We consider fine-tuning a pretrained deep neural network on a target task. We study the generalization properties of fine-tuning to understand the problem of overfitting, which has…
Improved Regularization and Robustness for Fine-tuning in Neural Networks
Dongyue Li, Hongyang R. Zhang
A widely used algorithm for transfer learning is fine-tuning, where a pre-trained model is fine-tuned on a target task with a small amount of labeled data. When the capacity of the…