• Publications
  • Influence
A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
TLDR
This paper uses target-opinion word pairs as “supervision” as a variational approach to weakly supervised document-level multi-aspect sentiment classification and can be comparable to the state-of-the-art supervised method with hundreds of labels per aspect.
MetaPhys: few-shot adaptation for non-contact physiological measurement
TLDR
A novel meta-learning approach for personalized video-based cardiac measurement for non-contact pulse and heart rate monitoring called MetaPhys, which uses only 18-seconds of video for customization and works effectively in both supervised and unsupervised manners.
Neural Subgraph Isomorphism Counting
TLDR
Experimental results show that learning based subgraph isomorphism counting can speed up the traditional algorithm, VF2, 10-1,000 times with acceptable errors and Domain adaptation based on fine-tuning also shows the usefulness of the approach in real-world applications.
Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification
TLDR
A path cost-sensitive learning algorithm is proposed to utilize the structural information and further make use of unlabeled and weakly-labeled data and introduce path constraints into the learning algorithm to incorporate theStructural information of the class hierarchy.
Matching-Theory-Based Low-Latency Scheme for Multitask Federated Learning in MEC Networks
TLDR
An algorithm for large-scale matching with the incomplete preference list to address the problem of almost impossible to know the details of every individual of the other side so that the complete preference list (CPL) cannot be built in reality is proposed.
Automatic Feature Engineering for Bus Passenger Flow Prediction Based on Modular Convolutional Neural Network
TLDR
This paper analyzes the passenger flow from scopes on both macroscopic and microscopic levels, in order to take full advantage of the information from a variety of views and inspired by the feature engineering of decision-tree-based models, a modular convolutional neural network is designed.
...
...