Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including …
Deep learning on graphs has recently achieved remarkable success on a variety of tasks, while such success relies heavily on the massive and carefully labeled data. However …
S Pan, L Xia, L Xu, Z Li - BMC bioinformatics, 2023 - Springer
Background Drug–target affinity (DTA) prediction is a critical step in the field of drug discovery. In recent years, deep learning-based methods have emerged for DTA prediction …
K Wang, Y Zhu, T Zang, C Wang, K Liu… - ACM Transactions on …, 2023 - dl.acm.org
Review-based recommender systems explore semantic aspects of users' preferences by incorporating user-generated reviews into rating-based models. Recent works have …
Recent contrastive based unsupervised object recognition methods leverage a Siamese architecture, which has two branches composed of a backbone, a projector layer, and an …
N Liu, S Jian, D Li, H Xu - Proceedings of the 31st ACM International …, 2022 - dl.acm.org
Graph pooling plays a vital role in learning graph embeddings. Due to the lack of label information, unsupervised graph pooling has received much attention, primarily via mutual …
In recent years, graph representation learning has achieved remarkable success while suffering from low-quality data problems. As a mature technology to improve data quality in …
Medical image datasets are often imbalanced due to biases in data collection and limitations in acquiring data for rare conditions. Addressing class imbalance is crucial for developing …
S Xu, L Wang, X Jia - Neural Processing Letters, 2023 - Springer
Studies on graph contrastive learning, which is an effective way of self-supervision, have achieved excellent experimental performance. Most existing methods generate two …