Boosting for transfer learning

By Wenyuan Dai, Qiang Yang, Gui-Rong Xue, Yong Yu. 2007

1,878 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Representation & Self-Supervised Learning

Citations in the corpus

Measuring Catastrophic Forgetting in Neural Networks (2017, methodology): “For the explicit methods, such as Learn++ and TradaBoost, this prevents forgetting because an entirely new sub-network is trained for a new batch (Polikar et al. 2001; Dai et al. 2007).”
Memory Efficient Experience Replay for Streaming Learning (2018, methodology): “Ensembling methods train multiple models and combine their outputs to make predictions [17], [21], [62], [65], [70].”
Task-Free Continual Learning via Online Discrepancy Distance Learning (2022, neutral): “One of the most popular approaches to relieve forgetting is by imposing a regularization loss within the optimization procedure [7, 11, 13, 16, 19, 25, 26, 31, 34, 35, 40, 41, 57], where the network’s parameters which are important to the past tasks are penalized when updating.”
Learning latent representations across multiple data domains using Lifelong VAEGAN (2020, background): “Regularization approaches in order to alleviate catastrophic forgetting add an auxiliary term that penalizes changes in the weights when the model is trained on a new task [14,26,29,33,38,48,54,60].”
A Comprehensive Survey on Transfer Learning (2019, methodology): “TrAdaBoost has a relatively good performance in this experiment because it uses the labels of the instances in the target domain to reduce the impact of the distribution difference.”
A Survey on Deep Transfer Learning (2018, methodology): “[4], [27], [20], [24], [10], [26], [11] Mapping-based Mapping instances from two domains into a new data space with better similarity.”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “data to actively select unlabeled target samples to be added to the training sets. [252] describes an active learning method for relevant target data selection and labeling, which combines TrAdaBoost [49] with standard SVM. [224], (see also Chapter 15), uses active learning and DA techniques to gene”
RODEO: Replay for Online Object Detection (2020, neutral): “work sparsely updates weights to mitigate interference [8], 3) ensembling multiple classifiers together [9, 11, 43, 47, 53], and 4) rehearsal/replay models that store a subset of previous training inputs (or generate previous inputs) to mix with new examples when updating the network [4, 16, 17, 21,”
Scalable Transfer Learning with Expert Models (2020, methodology): “One family of methods creates a single training dataset, where source instances are re-weighted according to their relevance (Dai et al., 2007; Pardoe & Stone, 2010; Wan et al., 2011; Xu et al., 2017).”
SpotTune: Transfer Learning Through Adaptive Fine-Tuning (2018, methodology): “Early approaches have concentrated on shallow classifiers, using techniques such as instance re-weighting [50, 12], model adaptation [11, 52], and feature space alignment [44, 35, 18].”
Predicting positive and negative links in signed social networks by transfer learning (2013, methodology): “[3] for instance weighting in our transfer learning framework.”
Continual Learning in Deep Neural Network by Using a Kalman Optimiser (2019, methodology): “To solve this problem, ensemble learning is among the solutions that are proposed in the existing work (Woźniak et al., 2014; Polikar et al., 2001; Dai et al., 2007).”
It's who you know: graph mining using recursive structural features (2011, background): “Representative work includes multi-label text classification [30, 13], crossdomain sentiment prediction [4, 6, 15], intrusion detection [12], verb argument classification [19], cross-lingual classification [25], and cross-domain relation extraction [29].”
Survey : Domain Adaptation Algorithms for Natural Language Processing (2012, positive): “.3.2 Self-training and TrAdaBoost Xu, Xu, and Wang (2011) studied domain adaptation algorithms for cross-lingual sentiment analysis, which addresses instance selection problem by using TrAdaBoost (Dai et al., 2007) and Transfer Self-training.”
Bregman Divergence-Based Regularization for Transfer Subspace Learning (2010, background): “It is a popular learning scheme by considering the auxiliary information, which can be transferred from the auxiliary tasks to the target tasks for boosting the ultimate learning performance [1].”