Search Results for author:
Found 2 papers, 0 papers with code
Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network
Under circumstances of heterophily, where nodes with different labels tend to be connected based on semantic meanings, Graph Neural Networks (GNNs) often exhibit suboptimal performance.
Ranked #17 on
Node Classification
on Texas
TaskDrop: A Competitive Baseline for Continual Learning of Sentiment Classification
In this paper, we study the multi-task sentiment classification problem in the continual learning setting, i. e., a model is sequentially trained to classifier the sentiment of reviews of products in a particular category.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
