相关论文: Evaluating Data Influence in Meta Learning

In this work, we investigate the potential of improving multi-task training and also leveraging it for transferring in the reinforcement learning setting. We identify several challenges towards this goal and propose a transferring approach…

Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework, Infusion, uses scalable influence-function approximations to…

Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by…

Federated learning enables many applications benefiting distributed and private datasets of a large number of potential data-holding clients. However, different clients usually have their own particular objectives in terms of the tasks to…

Confidence estimation, a task that aims to evaluate the trustworthiness of the model's prediction output during deployment, has received lots of research attention recently, due to its importance for the safe deployment of deep models.…

Meta-learning of shared initialization parameters has shown to be highly effective in solving few-shot learning tasks. However, extending the framework to many-shot scenarios, which may further enhance its practicality, has been relatively…

Training data attribution (TDA) methods aim to attribute model outputs back to specific training examples, and the application of these methods to large language model (LLM) outputs could significantly advance model transparency and data…

Influence functions approximate the "influences" of training data-points for test predictions and have a wide variety of applications. Despite the popularity, their computational cost does not scale well with model and training data size.…

Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans. Different meta-learning approaches all work under/with the mini-batch episodic training framework. Such framework naturally gives the information about…

Meta-learning is a powerful paradigm for tackling few-shot tasks. However, recent studies indicate that models trained with the whole-class training strategy can achieve comparable performance to those trained with meta-learning in few-shot…

In this paper we will discuss metalearning and how we can go beyond the current classical learning paradigm. We will first address the importance of inductive biases in the learning process and what is at stake: the quantities of data…

Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics to rank models…

Data valuation is a ML field that studies the value of training instances towards a given predictive task. Although data bias is one of the main sources of downstream model unfairness, previous work in data valuation does not consider how…

Parameter estimation in empirical fields is usually undertaken using parametric models, and such models readily facilitate statistical inference. Unfortunately, they are unlikely to be sufficiently flexible to be able to adequately model…

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes…

Large language models (LLMs) have demonstrated remarkable reasoning capabilities in math and coding, often bolstered by post-training on the chain-of-thoughts (CoTs) generated by stronger models. However, existing strategies for curating…

Multi-task learning aims to boost the generalization performance of multiple related tasks simultaneously by leveraging information contained in those tasks. In this paper, we propose a multi-task learning framework, where we utilize prior…

A learning task, understood as the problem of fitting a parametric model from supervised data, fundamentally requires the dataset to be large enough to be representative of the underlying distribution of the source. When data is limited,…

Metalearning and multitask learning are two frameworks for solving a group of related learning tasks more efficiently than we could hope to solve each of the individual tasks on their own. In multitask learning, we are given a fixed set of…

Deep neural network based recommendation systems have achieved great success as information filtering techniques in recent years. However, since model training from scratch requires sufficient data, deep learning-based recommendation…