Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment

By Dinghan Shen, Xinyuan Zhang, Ricardo Henao, Lawrence Carin. 2018

26 citations recorded by the source corpus.

Network embeddings, which learns low-dimensional representations for each vertex in a large-scale network, have received considerable attention in recent years. For a wide range of applications, vertices in a network are typically accompanied by rich textual information such as user profiles, paper abstracts, etc. In this paper, we propose to incorporate semantic features into network embeddings by matching important words between text sequences for all pairs of vertices. We introduce an word-by-word alignment framework that measures the compatibility of embeddings between word pairs, and then adaptively accumulates these alignment features with a simple yet effective aggregation function. In experiments, we evaluate the proposed framework on three real-world benchmarks for downstream tasks, including link prediction and multi-label vertex classification. The experimental results demonstrate that our model outperforms state-of-the-art network embedding methods by a large margin.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Nan Duan
2. Mohit Bansal
3. Daniel S. Weld
4. Iz Beltagy
5. Arman Cohan
6. Duyu Tang
7. Doug Downey
8. M. Zhou

In Statistical and Nonlinear Physics

1. M. Zhou
2. Sergey Feldman
3. Jingjing Xu

In Natural Language Processing

1. Daniel S. Weld
2. Arman Cohan
3. Nan Duan
4. Iz Beltagy
5. Doug Downey
6. Duyu Tang
7. M. Zhou
8. Jian Yin

Citations in the corpus

• Reasoning Over Semantic-Level Graph for Fact Checking (2019, methodology): “Inspired by Shen et al. (2018), we design our alignment function as: where W a ∈ R d × 4 ∗ d is a weight matrix and (cid:12) is element-wise Hadamard product.”
• SPECTER: Document-level Representation Learning using Citation-informed Transformers (2020, background): “Other relevant work combines textual features with network structure (Tu et al., 2017; Zhang et al., 2018; Bhagavatula et al., 2018; Shen et al., 2018; Chen et al., 2019; Wang et al., 2019).”