相关论文: Not All Models Are Equal: Predicting Model Transfe…

Recently, transfer learning and self-supervised learning have gained significant attention within the medical field due to their ability to mitigate the challenges posed by limited data availability, improve model generalisation, and reduce…

This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DNNs, we may easily collect hundreds of checkpoints from…

Transfer learning is often used to decrease the computational cost of model training, as fine-tuning a model allows a downstream task to leverage the features learned from the pre-training dataset and quickly adapt them to a new task. This…

Object detection, segmentation and classification are three common tasks in medical image analysis. Multi-task deep learning (MTL) tackles these three tasks jointly, which provides several advantages saving computing time and resources and…

Training data attribution (TDA) techniques find influential training data for the model's prediction on the test data of interest. They approximate the impact of down- or up-weighting a particular training sample. While conceptually useful,…

In this paper, we propose a new method called ProfWeight for transferring information from a pre-trained deep neural network that has a high test accuracy to a simpler interpretable model or a very shallow network of low complexity and a…

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…

Obtaining labeled data to train a model for a task of interest is often expensive. Prior work shows training models on multitask data augmented with task descriptions (prompts) effectively transfers knowledge to new tasks. Towards…

Finetuning foundation models for specific tasks is an emerging paradigm in modern machine learning. The efficacy of task-specific finetuning largely depends on the selection of appropriate training data. We present TSDS (Task-Specific Data…

This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks. Unlike most existing transfer learning methods that focus on fixing the discrepancy between supervised tasks, we…

In recent years, Graph Neural Network (GNN) based models have shown promising results in simulating physics of complex systems. However, training dedicated graph network based physics simulators can be costly, as most models are confined to…

Enabling robots to learn novel tasks in a data-efficient manner is a long-standing challenge. Common strategies involve carefully leveraging prior experiences, especially transition data collected on related tasks. Although much progress…

Domain adaptation is the supervised learning setting in which the training and test data are sampled from different distributions: training data is sampled from a source domain, whilst test data is sampled from a target domain. This paper…

Diffusion models have significantly advanced the field of generative modeling. However, training a diffusion model is computationally expensive, creating a pressing need to adapt off-the-shelf diffusion models for downstream generation…

Precise load forecasting in buildings could increase the bill savings potential and facilitate optimized strategies for power generation planning. With the rapid evolution of computer science, data-driven techniques, in particular the Deep…

Backpropagation has long been criticized for being biologically implausible due to its reliance on concepts that are not viable in natural learning processes. Two core issues are the weight transport and update locking problems caused by…

Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks,…

Many challenging real-world problems require the deployment of ensembles multiple complementary learning models to reach acceptable performance levels. While effective, applying the entire ensemble to every sample is costly and often…

Embedding models have become essential tools in both natural language processing and computer vision, enabling efficient semantic search, recommendation, clustering, and more. However, the high memory and computational demands of…

We propose a semi-supervised text classifier based on self-training using one positive and one negative property of neural networks. One of the weaknesses of self-training is the semantic drift problem, where noisy pseudo-labels accumulate…