相关论文: Zero-Shot AutoML with Pretrained Models

Modern machine learning models are expensive to train, and there is a growing concern about the challenge of retroactively removing specific training data. Achieving exact unlearning in deep learning pipelines--producing models as if…

How reliably can a small language model estimate its own correctness? The answer determines whether local-to-cloud routing-escalating queries a cheap local model cannot handle-can work without supervised training data. As inference costs…

Machine learning (ML) methods have been developing rapidly, but configuring and selecting proper methods to achieve a desired performance is increasingly difficult and tedious. To address this challenge, automated machine learning (AutoML)…

Deep Neural Networks (DNNs) often rely on very large datasets for training. Given the large size of such datasets, it is conceivable that they contain certain samples that either do not contribute or negatively impact the DNN's…

How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context…

Despite the impressive progress of general face detection, the tuning of hyper-parameters and architectures is still critical for the performance of a domain-specific face detector. Though existing AutoML works can speedup such process,…

We introduce ProLoRA, enabling zero-shot adaptation of parameter-efficient fine-tuning in text-to-image diffusion models. ProLoRA transfers pre-trained low-rank adjustments (e.g., LoRA) from a source to a target model without additional…

Numerically solving a large parametric nonlinear dynamical system is challenging due to its high complexity and the high computational costs. In recent years, machine-learning-aided surrogates are being actively researched. However, many…

Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…

Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information, etc. With the increasing need to deploy such systems in new domains,…

Pretrained multilingual models are able to perform cross-lingual transfer in a zero-shot setting, even for languages unseen during pretraining. However, prior work evaluating performance on unseen languages has largely been limited to…

Classical deep neural networks are limited in their ability to learn from emerging streams of training data. When trained sequentially on new or evolving tasks, their performance degrades sharply, making them inappropriate in real-world use…

One of the consequences of passing from mass production to mass customization paradigm in the nowadays industrialized world is the need to increase flexibility and responsiveness of manufacturing companies. The high-mix / low-volume…

Semi-supervised learning (SSL) alleviates the cost of data labeling process by exploiting unlabeled data and has achieved promising results. Meanwhile, with the development of large foundation models, exploiting pre-trained models becomes a…

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to…

Being able to predict the remaining useful life (RUL) of an engineering system is an important task in prognostics and health management. Recently, data-driven approaches to RUL predictions are becoming prevalent over model-based approaches…

We propose an AutoML system that enables model selection on clustering problems by leveraging optimal transport-based dataset similarity. Our objective is to establish a comprehensive AutoML pipeline for clustering problems and provide…

A precise forecast for droughts is of considerable value to scientific research, agriculture, and water resource management. With emerging developments of data-driven approaches for hydro-climate modeling, this paper investigates an…

Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…

We propose a simple yet a novel approach to improve completion in domain modeling activities. Our approach exploits the power of large language models by using few-shot prompt learning without the need to train or fine-tune those models…