Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction

Abstract

Click-through rate (CTR) prediction is an essential task in web applications such as online advertising and recommender systems, whose features are usually in multi-field form. The key of this task is to model feature interactions among different feature fields. Recently proposed deep learning based models follow a general paradigm: raw sparse input multi-filed features are first mapped into dense field embedding vectors, and then simply concatenated together to feed into deep neural networks (DNN) or other specifically designed networks to learn high-order feature interactions. However, the simple \emph{unstructured combination} of feature fields will inevitably limit the capability to model sophisticated interactions among different fields in a sufficiently flexible and explicit fashion. In this work, we propose to represent the multi-field features in a graph structure intuitively, where each node corresponds to a feature field and different fields can interact through edges. The task of modeling feature interactions can be thus converted to modeling node interactions on the corresponding graph. To this end, we design a novel model Feature Interaction Graph Neural Networks (Fi-GNN). Taking advantage of the strong representative power of graphs, our proposed model can not only model sophisticated feature interactions in a flexible and explicit fashion, but also provide good model explanations for CTR prediction. Experimental results on two real-world datasets show its superiority over the state-of-the-arts.

arXiv comment10 pages, accepted by the 2019 Conference on Information and Knowledge Management (CIKM-2019)

References in corpus (12)

• Distributed Representations of Words and Phrases and their Compositionality
• DeepWalk: Online Learning of Social Representations
• Semi-Supervised Classification with Graph Convolutional Networks
• LINE: Large-scale Information Network Embedding
• Inductive Representation Learning on Large Graphs
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Graph Neural Networks: A Review of Methods and Applications
• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
• Gated Graph Sequence Neural Networks
• Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction
• Constructing Narrative Event Evolutionary Graph for Script Event Prediction

Cited by in corpus (38)

• Click-Through Rate Prediction in Online Advertising: A Literature Review
• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
• Graph Convolution Machine for Context-aware Recommender System
• Multi-behavior Self-supervised Learning for Recommendation
• EulerNet: Adaptive Feature Interaction Learning via Euler's Formula for CTR Prediction
• TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search
• Neural Graph Matching based Collaborative Filtering
• CatGCN: Graph Convolutional Networks with Categorical Node Features
• Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks
• Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction
• TFNet: Multi-Semantic Feature Interaction for CTR Prediction
• Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation
• HIEN: Hierarchical Intention Embedding Network for Click-Through Rate Prediction
• Graph-based Hierarchical Relevance Matching Signals for Ad-hoc Retrieval
• Explicit Feature Interaction-aware Graph Neural Networks
• Deep Evolutional Instant Interest Network for CTR Prediction in Trigger-Induced Recommendation
• User Response Prediction in Online Advertising
• GraphFM: Graph Factorization Machines for Feature Interaction Modeling
• Deep Learning for Click-Through Rate Estimation
• Graph Factorization Machines for Cross-Domain Recommendation
• ContextNet: A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding
• Open Benchmarking for Click-Through Rate Prediction
• Heterogeneous Graph Collaborative Filtering
• Click-Through Rate Prediction Using Graph Neural Networks and Online Learning
• MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction
• Generalized Embedding Machines for Recommender Systems
• Dynamic Graph Collaborative Filtering
• Adaptive Learning on User Segmentation: Universal to Specific Representation via Bipartite Neural Interaction
• AEFE: Automatic Embedded Feature Engineering for Categorical Features
• Toward a benchmark for CTR prediction in online advertising: datasets, evaluation protocols and perspectives
• GraphSeam: Supervised Graph Learning Framework for Semantic UV Mapping
• Ensemble Knowledge Distillation for CTR Prediction
• Dual Graph enhanced Embedding Neural Network for CTR Prediction
• Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction
• FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data
• Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling
• Dual-Stream MLP is All You Need for CTR Prediction
• Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey