# IntentGC: a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation

## TL;DR

IntentGC introduces a scalable graph convolution framework that effectively fuses heterogeneous information for recommendation, addressing data sparsity and automatically learning relationship importance, validated by large-scale experiments and online tests.

## Contribution

The paper proposes IntentGC, a novel graph convolutional framework that leverages heterogeneous auxiliary data and learns relationship importance nonlinearly, with a faster variant IntentNet for web-scale applications.

## Key findings

- Outperforms state-of-the-art algorithms on large-scale datasets
- Demonstrates effectiveness through online A/B tests in Alibaba
- Automatically learns the importance of different relationships

## Abstract

The remarkable progress of network embedding has led to state-of-the-art algorithms in recommendation. However, the sparsity of user-item interactions (i.e., explicit preferences) on websites remains a big challenge for predicting users' behaviors. Although research efforts have been made in utilizing some auxiliary information (e.g., social relations between users) to solve the problem, the existing rich heterogeneous auxiliary relationships are still not fully exploited. Moreover, previous works relied on linearly combined regularizers and suffered parameter tuning. In this work, we collect abundant relationships from common user behaviors and item information, and propose a novel framework named IntentGC to leverage both explicit preferences and heterogeneous relationships by graph convolutional networks. In addition to the capability of modeling heterogeneity, IntentGC can learn the importance of different relationships automatically by the neural model in a nonlinear sense. To apply IntentGC to web-scale applications, we design a faster graph convolutional model named IntentNet by avoiding unnecessary feature interactions. Empirical experiments on two large-scale real-world datasets and online A/B tests in Alibaba demonstrate the superiority of our method over state-of-the-art algorithms.