@article{Shi_Fan_Kwok_2020, title={Effective Decoding in Graph Auto-Encoder Using Triadic Closure}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/5437}, DOI={10.1609/aaai.v34i01.5437}, abstractNote={<p>The (variational) graph auto-encoder and its variants have been popularly used for representation learning on graph-structured data. While the encoder is often a powerful graph convolutional network, the decoder reconstructs the graph structure by only considering two nodes at a time, thus ignoring possible interactions among edges. On the other hand, structured prediction, which considers the whole graph simultaneously, is computationally expensive. In this paper, we utilize the well-known <em>triadic closure</em> property which is exhibited in many real-world networks. We propose the triad decoder, which considers and predicts the three edges involved in a local triad together. The triad decoder can be readily used in any graph-based auto-encoder. In particular, we incorporate this to the (variational) graph auto-encoder. Experiments on link prediction, node clustering and graph generation show that the use of triads leads to more accurate prediction, clustering and better preservation of the graph characteristics.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Shi, Han and Fan, Haozheng and Kwok, James T.}, year={2020}, month={Apr.}, pages={906-913} }