Self-supervised representation learning: Introduction, advances, and challenges

L Ericsson, H Gouk, CC Loy… - IEEE Signal Processing …, 2022 - ieeexplore.ieee.org
Self-supervised representation learning (SSRL) methods aim to provide powerful, deep
feature learning without the requirement of large annotated data sets, thus alleviating the …

[HTML][HTML] Graph neural networks: A review of methods and applications

J Zhou, G Cui, S Hu, Z Zhang, C Yang, Z Liu, L Wang… - AI open, 2020 - Elsevier
Lots of learning tasks require dealing with graph data which contains rich relation
information among elements. Modeling physics systems, learning molecular fingerprints …

[HTML][HTML] Pre-trained models: Past, present and future

X Han, Z Zhang, N Ding, Y Gu, X Liu, Y Huo, J Qiu… - AI Open, 2021 - Elsevier
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved
great success and become a milestone in the field of artificial intelligence (AI). Owing to …

Self-supervised learning: Generative or contrastive

X Liu, F Zhang, Z Hou, L Mian, Z Wang… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
Deep supervised learning has achieved great success in the last decade. However, its
defects of heavy dependence on manual labels and vulnerability to attacks have driven …

Gcc: Graph contrastive coding for graph neural network pre-training

J Qiu, Q Chen, Y Dong, J Zhang, H Yang… - Proceedings of the 26th …, 2020 - dl.acm.org
Graph representation learning has emerged as a powerful technique for addressing real-
world problems. Various downstream graph learning tasks have benefited from its recent …

Heterogeneous graph transformer

Z Hu, Y Dong, K Wang, Y Sun - Proceedings of the web conference 2020, 2020 - dl.acm.org
Recent years have witnessed the emerging success of graph neural networks (GNNs) for
modeling structured data. However, most GNNs are designed for homogeneous graphs, in …

Gpt-gnn: Generative pre-training of graph neural networks

Z Hu, Y Dong, K Wang, KW Chang, Y Sun - Proceedings of the 26th ACM …, 2020 - dl.acm.org
Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-
structured data. However, training GNNs requires abundant task-specific labeled data …

A comprehensive survey on automatic knowledge graph construction

L Zhong, J Wu, Q Li, H Peng, X Wu - ACM Computing Surveys, 2023 - dl.acm.org
Automatic knowledge graph construction aims at manufacturing structured human
knowledge. To this end, much effort has historically been spent extracting informative fact …

Sugar: Subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism

Q Sun, J Li, H Peng, J Wu, Y Ning, PS Yu… - Proceedings of the web …, 2021 - dl.acm.org
Graph representation learning has attracted increasing research attention. However, most
existing studies fuse all structural features and node attributes to provide an overarching …

Oag-bench: a human-curated benchmark for academic graph mining

F Zhang, S Shi, Y Zhu, B Chen, Y Cen, J Yu… - Proceedings of the 30th …, 2024 - dl.acm.org
With the rapid proliferation of scientific literature, versatile academic knowledge services
increasingly rely on comprehensive academic graph mining. Despite the availability of …