TY - JOUR AU - Kefato, Zekarias AU - Girdzijauskas, Sarunas PY - 2020/05/26 Y2 - 2024/03/28 TI - Gossip and Attend: Context-Sensitive Graph Representation Learning JF - Proceedings of the International AAAI Conference on Web and Social Media JA - ICWSM VL - 14 IS - 1 SE - Full Papers DO - 10.1609/icwsm.v14i1.7305 UR - https://ojs.aaai.org/index.php/ICWSM/article/view/7305 SP - 351-359 AB - <p>Graph representation learning (GRL) is a powerful technique for learning low-dimensional vector representation of high-dimensional and often sparse graphs. Most studies explore the structure and metadata associated with the graph using random walks and employ an unsupervised or semi-supervised learning schemes. Learning in these methods is context-free, resulting in only a single representation per node. Recently studies have argued on the adequacy of a single representation and proposed context-sensitive approaches, which are capable of extracting multiple node representations for different contexts. This proved to be highly effective in applications such as link prediction and ranking.</p><p>However, most of these methods rely on additional textual features that require complex and expensive RNNs or CNNs to capture high-level features or rely on a community detection algorithm to identify multiple contexts of a node.</p><p>In this study we show that in-order to extract high-quality context-sensitive node representations it is not needed to rely on supplementary node features, nor to employ computationally heavy and complex models. We propose Goat, a context-sensitive algorithm inspired by gossip communication and a mutual attention mechanism simply over the structure of the graph. We show the efficacy of Goat using 6 real-world datasets on link prediction and node clustering tasks and compare it against 12 popular and state-of-the-art (SOTA) baselines. Goat consistently outperforms them and achieves up to 12% and 19% gain over the best performing methods on link prediction and clustering tasks, respectively.</p> ER -