DeepAI AI Chat
Log In Sign Up

Link Prediction with Mutual Attention for Text-Attributed Networks

by   Robin Brochier, et al.
Universite Lumiere Lyon 2

In this extended abstract, we present an algorithm that learns a similarity measure between documents from the network topology of a structured corpus. We leverage the Scaled Dot-Product Attention, a recently proposed attention mechanism, to design a mutual attention mechanism between pairs of documents. To train its parameters, we use the network links as supervision. We provide preliminary experiment results with a citation dataset on two prediction tasks, demonstrating the capacity of our model to learn a meaningful textual similarity.


page 1

page 2


Query-based Attention CNN for Text Similarity Map

In this paper, we introduce Query-based Attention CNN(QACNN) for Text Si...

Aggregated Sparse Attention for Steering Angle Prediction

In this paper, we apply the attention mechanism to autonomous driving fo...

Learning Hard Retrieval Cross Attention for Transformer

The Transformer translation model that based on the multi-head attention...

Adversarial Robustness of Similarity-Based Link Prediction

Link prediction is one of the fundamental problems in social network ana...

A comparative analysis of local network similarity measurements: application to author citation networks

Understanding the evolution of paper and author citations is of paramoun...

Attention improves concentration when learning node embeddings

We consider the problem of predicting edges in a graph from node attribu...

Implicit Kernel Attention

Attention compute the dependency between representations, and it encoura...