Name
Abstract | ||
|---|---|---|
Adding attributes for nodes to network helps to improve the ability of the learned joint representation to depict features from topology and attributes simultaneously. Recent research on the joint has exhibited a promising performance on a variety of tasks by jointly the two spaces. However, due to the indispensable requirement of globality based information, present approaches contain a flaw of in-scalability. Here we propose emph{SANE}, a scalable attribute-aware network algorithm with locality, to learn the joint representation from topology and attributes. By enforcing the alignment of a local linear relationship between each node and its K-nearest neighbors in topology and attribute space, the joint representations are more informative comparing with a single representation from topology or attributes alone. And we argue that the locality in emph{SANE} is the key to the joint representation at scale. By using several real-world networks from diverse domains, We demonstrate the efficacy of emph{SANE} in performance and scalability aspect. Overall, for performance on label classification, SANE successfully reaches up to the highest F1-score on most datasets, and even closer to the baseline method that needs label information as extra inputs, compared with other state-of-the-art joint representation algorithms. Whatu0027s more, emph{SANE} has an up to 71.4% performance gain compared with the single topology-based algorithm. For scalability, we have demonstrated the linearly time complexity of emph{SANE}. In addition, we intuitively observe that when the network size scales to 100,000 nodes, the learning joint embedding step of emph{SANE} only takes $approx10$ seconds. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Learning | Network size,Locality,Embedding,Theoretical computer science,Artificial intelligence,Network embedding,Time complexity,Mathematics,Machine learning,Globality,Scalability |
DocType | Volume | Citations |
Journal | abs/1804.07152 | 0 |
PageRank | References | Authors |
0.34 | 1 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Weiyi Liu | 1 | 7 | 3.14 |
| Zhining Liu | 2 | 0 | 0.34 |
| Toyotaro Suzumura | 3 | 476 | 52.85 |
| Guang-min Hu | 4 | 87 | 19.78 |