Linked Recurrent Neural Networks

TL;DR

This paper introduces LinkedRNN, a novel recurrent neural network model that effectively captures both sequential and link information in linked data, addressing challenges of non-i.i.d. sequences in real-world applications.

Contribution

The paper proposes a new LinkedRNN model that coherently integrates link information with sequential data, improving modeling of linked sequences.

Findings

LinkedRNN outperforms existing models on real-world datasets.

Link information enhances the modeling of sequential data.

Experimental results validate the effectiveness of the proposed approach.

Abstract

Recurrent Neural Networks (RNNs) have been proven to be effective in modeling sequential data and they have been applied to boost a variety of tasks such as document classification, speech recognition and machine translation. Most of existing RNN models have been designed for sequences assumed to be identically and independently distributed (i.i.d). However, in many real-world applications, sequences are naturally linked. For example, web documents are connected by hyperlinks; and genes interact with each other. On the one hand, linked sequences are inherently not i.i.d., which poses tremendous challenges to existing RNN models. On the other hand, linked sequences offer link information in addition to the sequential information, which enables unprecedented opportunities to build advanced RNN models. In this paper, we study the problem of RNN for linked sequences. In particular, we introduce a principled approach to capture link information and propose a linked Recurrent Neural Network (LinkedRNN), which models sequential and link information coherently. We conduct experiments on real-world datasets from multiple domains and the experimental results validate the effectiveness of the proposed framework.