SENSE: Semantically Enhanced Node Sequence Embedding
Preprint
Abstract
Effectively capturing graph node sequences in the form of vector embeddings is critical to many applications. We achieve this by (i) first learning vector embeddings of single graph nodes and (ii) then composing them to compactly represent node sequences. Specifically, we propose SENSE-S (Semantically Enhanced Node Sequence Embedding - for Single nodes), a skip-gram based novel embedding mechanism, for single graph nodes that co-learns graph structure as well as their textual descriptions. We demonstrate that SENSE-S vectors increase the accuracy of multi-label classification tasks by up to 50% and link-prediction tasks by up to 78% under a variety of scenarios using real datasets. Based on SENSE-S, we next propose generic SENSE to compute composite vectors that represent a sequence of nodes, where preserving the node order is important. We prove that this approach is efficient in embedding node sequences, and our experiments on real data confirm its high accuracy in node order decoding.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Attributed Social Network EmbeddingIEEE Transactions on Knowledge and Data Engineering, 2018
- Accelerated Attributed Network Embedding2017
- SSP: Semantic Space Projection for Knowledge Graph Embedding with Text DescriptionsProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Incorporating Knowledge Graph Embeddings into Topic ModelingProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Scalable Graph Embedding for Asymmetric ProximityProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding2017
- Probabilistic Latent Document Network Embedding2014
- Efficient Identification of Additive Link Metrics via Network Tomography2013
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank2013
- Neural network based language models for highly inflective languages2009