• Publications
  • Influence
A Survey on Transfer Learning
TLDR
A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. Expand
  • 9,685
  • 621
  • PDF
Domain Adaptation via Transfer Component Analysis
TLDR
We propose a novel feature extraction method, TCA, for domain adaptation, which can dramatically reduce the distance between domain distributions by projecting data onto the learned transfer components. Expand
  • 1,898
  • 400
  • PDF
Cross-domain sentiment classification via spectral feature alignment
TLDR
We propose a spectral feature alignment (SFA) algorithm to align domain-specific words from different domains into unified clusters, with the help of domain-independent words as a bridge. Expand
  • 627
  • 87
  • PDF
Transfer defect learning
TLDR
In this paper, we apply a state-of-the-art transfer learning approach, TCA, to make feature distributions in source and target projects similar. Expand
  • 299
  • 58
  • PDF
Adaptation Regularization: A General Framework for Transfer Learning
TLDR
We propose a novel transfer learning framework, referred to as Adaptation Regularization based Transfer Learning (ARTL), to model them in a unified way based on the structural risk minimization principle and the regularization theory. Expand
  • 304
  • 53
  • PDF
Transfer Learning via Dimensionality Reduction
TLDR
We propose a new dimensionality reduction method to find a low-dimensional latent feature space where the distributions between the source domain data and the target domain data are the same or close to each other. Expand
  • 527
  • 48
  • PDF
Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis
TLDR
In aspect-based sentiment analysis, extracting aspect terms along with the opinions being expressed from user-generated content is one of the most important subtasks. Expand
  • 171
  • 36
  • PDF
Domain Generalization with Adversarial Feature Learning
TLDR
We present a novel framework based on adversarial autoencoders to learn a generalized latent feature representation across domains for domain generalization. Expand
  • 150
  • 28
  • PDF
Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms
TLDR
We propose a novel deep learning model, named coupled multi-layer attentions, for the task of aspect and opinion terms co-extraction. Expand
  • 135
  • 27
  • PDF
Heterogeneous Transfer Learning for Image Classification
TLDR
We propose a heterogeneous transfer learning framework for image classification by exploring knowledge transfer from auxiliary unlabeled images and text data. Expand
  • 239
  • 20
  • PDF