Related papers: Characterizing and Avoiding Negative Transfer
Transfer learning, which is to improve the learning performance in the target domain by leveraging useful knowledge from the source domain, often requires that those two domains are very close, which limits its application scope. Recently,…
Distantly supervision automatically generates plenty of training samples for relation extraction. However, it also incurs two major problems: noisy labels and imbalanced training data. Previous works focus more on reducing wrongly labeled…
Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks. An important question is to determine task transferability, i.e. given a common…
Transfer learning is a powerful technique for knowledge-sharing between different tasks. Recent work has found that the representations of models with certain invariances, such as to adversarial input perturbations, achieve higher…
We study the transfer learning process between two linear regression problems. An important and timely special case is when the regressors are overparameterized and perfectly interpolate their training data. We examine a parameter transfer…
Machine learning is used for inference and decision making in wearable sensor systems. However, recent studies have found that machine learning algorithms are easily fooled by the addition of adversarial perturbations to their inputs. What…
Negative sampling approaches are prevalent in implicit collaborative filtering for obtaining negative labels from massive unlabeled data. As two major concerns in negative sampling, efficiency and effectiveness are still not fully achieved…
In this work, we study the transfer learning problem under high-dimensional generalized linear models (GLMs), which aim to improve the fit on target data by borrowing information from useful source data. Given which sources to transfer, we…
In many practical data mining scenarios, such as network intrusion detection, Twitter spam detection, and computer-aided diagnosis, a source domain that is different from but related to a target domain is very common. In addition, a large…
Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…
Transfer learning is beneficial for survival analysis, especially when the target study has a limited number of events. However, existing transfer learning methods rely on the restrictive assumption that the target and source studies share…
Adversarial attacks have verified the existence of the vulnerability of neural networks. By adding small perturbations to a benign example, adversarial attacks successfully generate adversarial examples that lead misclassification of deep…
Positive-Unlabeled (PU) learning presents unique challenges due to the lack of explicitly labeled negative samples, particularly in high-stakes domains such as fraud detection and medical diagnosis. To address data scarcity and privacy…
In this paper we propose an improved method for transfer learning that takes into account the balance between target and source data. This method builds on the state-of-the-art Multisource Tradaboost, but weighs the importance of each…
In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they…
As deep learning models are becoming larger and data-hungrier, there are growing ethical, legal and technical concerns over use of data: in practice, agreements on data use may change over time, rendering previously-used training data…
This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy. It leverages ensemble learning and includes diverse, complementary…
With the ever-increasing complexity of large-scale pre-trained models coupled with a shortage of labeled data for downstream training, transfer learning has become the primary approach in many fields, including natural language processing,…
Supervised transfer learning has received considerable attention due to its potential to boost the predictive power of machine learning in scenarios where data are scarce. Generally, a given set of source models and a dataset from a target…
In the era of transfer learning, training neural networks from scratch is becoming obsolete. Transfer learning leverages prior knowledge for new tasks, conserving computational resources. While its advantages are well-documented, we uncover…