Related papers: Transfer Learning and the Early Estimation of Sing…
Learning from small amounts of labeled data is a challenge in the area of deep learning. This is currently addressed by Transfer Learning where one learns the small data set as a transfer task from a larger source dataset. Transfer Learning…
Harnessing the unique properties of quantum mechanics offers the possibility to deliver new technologies that can fundamentally outperform their classical counterparts. These technologies only deliver advantages when components operate with…
Multi-source transfer learning provides an effective solution to data scarcity in real-world supervised learning scenarios by leveraging multiple source tasks. In this field, existing works typically use all available samples from sources…
Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the…
Conventional colorimetric sensing methods typically rely on signal intensity at a single wavelength, often selected heuristically based on peak visual modulation. This approach overlooks the structured information embedded in full-spectrum…
The field of prosody transfer in speech synthesis systems is rapidly advancing. This research is focused on evaluating learning methods for adapting pre-trained monolingual text-to-speech (TTS) models to multilingual conditions, i.e.,…
Machine learning (ML) has become a versatile tool for analyzing anomalous diffusion trajectories, yet most existing pipelines are trained on large collections of simulated data. In contrast, experimental trajectories, such as those from…
Machine learning (ML) can facilitate efficient thermoelectric (TE) material discovery essential to address the environmental crisis. However, ML models often suffer from poor experimental generalizability despite high metrics. This study…
Ongoing or upcoming surveys such as Gaia, ZTF, or LSST will observe light-curves of billons or more astronomical sources. This presents new challenges for identifying interesting and important types of variability. Collecting a sufficient…
Semi-supervised learning (SSL) has become an interesting research area due to its capacity for learning in scenarios where both labeled and unlabeled data are available. In this work, we focus on the task of transduction - when the…
Monitoring data transfer performance is a crucial task in scientific computing networks. By predicting performance early in the communication phase, potentially sluggish transfers can be identified and selectively monitored, optimizing…
Transferability metrics is a maturing field with increasing interest, which aims at providing heuristics for selecting the most suitable source models to transfer to a given target dataset, without fine-tuning them all. However, existing…
Multi-source sequence generation (MSG) is an important kind of sequence generation tasks that takes multiple sources, including automatic post-editing, multi-source translation, multi-document summarization, etc. As MSG tasks suffer from…
Extracting actionable information rapidly from data produced by instruments such as the Linac Coherent Light Source (LCLS-II) and Advanced Photon Source Upgrade (APS-U) is becoming ever more challenging due to high (up to TB/s) data rates.…
Recent years have witnessed increasing interests in prompt-based learning in which models can be trained on only a few annotated instances, making them suitable in low-resource settings. When using prompt-based learning for text…
We investigate the transferability of machine learning interatomic potentials across concentration variations in chemically similar systems, using aqueous potassium hydroxide solutions as a case study. Despite containing identical chemical…
In image Super-Resolution (SR), relying on large datasets for training is a double-edged sword. While offering rich training material, they also demand substantial computational and storage resources. In this work, we analyze dataset…
Plant phenotyping (Guo et al. 2021; Pieruschka et al. 2019) focuses on studying the diverse traits of plants related to the plants' growth. To be more specific, by accurately measuring the plant's anatomical, ontogenetical, physiological…
Transfer learning is a commonly used strategy for medical image classification, especially via pretraining on source data and fine-tuning on target data. There is currently no consensus on how to choose appropriate source data, and in the…
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets. Generally, more accurate models on the "upstream" dataset tend to…