Linlin Wang

Layer-wise contrastive network for unsupervised graph representation learning

2026 · Neurocomputing

Unsupervised graph representation learning has emerged as a cornerstone for extracting meaningful insights from complex relational data. While contrastive learning paradigms have achieved notable success, they traditionally rely on stochastic data augmentations to generate multiple …

Relation Classification via Multi-Level Attention CNNs

2016

Relation classification is a crucial ingredient in numerous information extraction systems seeking to mine structured facts from text. We propose a novel convolutional neural network architecture for this task, relying on two levels of attention …