Graham Bent
Research Subjects
Research Interests
Graham Bent has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Ananthram Swami
DEVCOM Army Research Lab, Adelphi, MD, USA
1 shared publication - Christopher Simpkin
Cardiff University Cardiff UK
1 shared publication - Heesung Kwon
U.S. Army Research Laboratory Adelphi Maryland U.S.A
1 shared publication - Liang Ma
Research Center IBM T. J. Watson Research Center Yorktown Yorktown NY NY USA USA
1 shared publication - Mudhakar Srivatsa
Thomas J. Watson Research Center
1 shared publication - Swati Rallapalli
IBM Research, IBM Research, Ossining, New York United States
1 shared publication
Latest Publications
- Open Access
SENSE: Semantically Enhanced Node Sequence Embedding
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.
Open AccessSENSE: Semantically Enhanced Node Sequence Embedding
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.