Improving Textual Network Embedding with Global Attention via Optimal Transport

Abstract

Constituting highly informative network embeddings is an important tool for network analysis. It encodes network topology, along with other useful side information, into low-dimensional node-based feature representations that can be exploited by statistical modeling. This work focuses on learning context-aware network embeddings augmented with text data. We reformulate the network-embedding problem, and present two novel strategies to improve over traditional attention mechanisms: ($i$) a content-aware sparse attention module based on optimal transport, and ($ii$) a high-level attention parsing module. Our approach yields naturally sparse and self-normalized relational inference. It can capture long-term interactions between sequences, thus addressing the challenges faced by existing textual network embedding schemes. Extensive experiments are conducted to demonstrate our model can consistently outperform alternative state-of-the-art methods.

References in corpus (11)

• Distributed Representations of Words and Phrases and their Compositionality
• word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
• Effective Approaches to Attention-based Neural Machine Translation
• Attentive Pooling Networks
• A Hierarchical Neural Autoencoder for Paragraphs and Documents
• A Regularized Framework for Sparse and Structured Neural Attention
• Adversarial Text Generation via Feature-Mover's Distance
• A General Framework for Content-enhanced Network Representation Learning
• Notes on Noise Contrastive Estimation and Negative Sampling
• Stochastic Answer Networks for Natural Language Inference
• Diffusion Maps for Textual Network Embedding

Cited by in corpus (1)

• Integrated Node Encoder for Labelled Textual Networks