Click-Through Rate Prediction with Multi-Modal Hypergraphs

  title={Click-Through Rate Prediction with Multi-Modal Hypergraphs},
  author={Li He and Hongxu Chen and Dingxian Wang and Shoaib Jameel and Philip S. Yu and Guandong Xu},
  journal={Proceedings of the 30th ACM International Conference on Information \& Knowledge Management},
  • Li HeHongxu Chen Guandong Xu
  • Published 6 September 2021
  • Computer Science
  • Proceedings of the 30th ACM International Conference on Information & Knowledge Management
Advertising is critical to many online e-commerce platforms such as e-Bay and Amazon. One of the important signals that these platforms rely upon is the click-through rate (CTR) prediction. The recent popularity of multi-modal sharing platforms such as TikTok has led to an increased interest in online micro-videos. It is, therefore, useful to consider micro-videos to help a merchant target micro-video advertising better and find users' favourites to enhance user experience. Existing works on… 

Figures and Tables from this paper

Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation

A Multi-Behavior Hypergraph-enhanced T ransformer framework (MBHT) to capture both short-term and long-term cross-type behavior dependencies, and incorporates the global multi-behavior dependency into the hypergraph neural architecture to capture the hierarchical long-range item correlations in a customized manner.

Incorporating a Topic Model into a Hypergraph Neural Network for Searching-Scenario Oriented Recommendations

A topic augmented hypergraph neural network framework is developed to predict the user’s purchase intention by connecting the latent topics embedded in a consumer's online queries to their click, purchase, and online review behavior, which aims at mining the connection information existing in the interaction graph domain.

Learning the User’s Deeper Preferences for Multi-modal Recommendation Systems

A novel module named Learning the User’s Deeper Preferences (LUDP) is proposed, which constructs the item-item modal similarity graph and user preference graph in each modality to explore the learning of item and user representation.

Hypergraph Contrastive Collaborative Filtering

A new self-supervised recommendation framework Hypergraph Contrastive Collaborative Filtering (HCCF) is proposed to jointly capture local and global collaborative relations with a hypergraph-enhanced cross-view contrastive learning architecture, and enhances the discrimination ability of GNN-based CF paradigm, in comprehensively capturing the complex high-order dependencies among users.

Exploiting Explicit and Implicit Item relationships for Session-based Recommendation

A dualgraph neural network is designed that leverages the feature representations extracted by two GNNs: a graph neural network with a single gate (SG-GNN) and an adaptive graph neuralnetwork (A-Gnn) that employs a self-learning strategy to capture implicit correlations among items.

APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction

This paper proposes ancient, effective, and universal module, named as Adaptive Parameter Generation network (APG), which can dynamically generate parameters for deep CTR models on-the-fly based on different instances and can reduce the time cost and memory usage compared to a regular deep CTR model.

Modeling Persuasion Factor of User Decision for Recommendation

This work presents the POEM (short for Persuasion factOr Effect Modeling) system, a proposed framework of modeling the effect of persuasion factors, and develops a prediction layer that fully considers the user sensitivity to the persuasion factors.

Geometric Inductive Matrix Completion: A Hyperbolic Approach with Unified Message Passing

This paper proposes Geometric Inductive Matrix Completion (GIMC) by introducing hyperbolic geometry and a unified message passing scheme into this generic task and is the first work defining continuous explicit feedback prediction within non-Euclidean space.

Simplifying Graph-based Collaborative Filtering for Recommendation

This paper removes non-linearities to enhance recommendation performance and obtains the initialization of the embedding for each node in the graph by computing the network embedding on the condensed graph, which alleviates the over smoothing problem in graph convolution aggregation operation with sparse interaction data.

AHP: Learning to Negative Sample for Hyperedge Prediction

This paper proposes AHP, an adversarial training-based hyperedge-prediction method that learns to sample negative examples without relying on any heuristic schemes, and shows that AHP generalizes better to negative examples of various natures.



Deep Session Interest Network for Click-Through Rate Prediction

A novel CTR model named Deep Session Interest Network (DSIN) is proposed that leverages users' multiple historical sessions in their behavior sequences and outperforms other state-of-the-art models on both datasets.

MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video

A Multi-modal Graph Convolution Network (MMGCN) framework built upon the message-passing idea of graph neural networks, which can yield modal-specific representations of users and micro-videos to better capture user preferences is designed.

Temporal Hierarchical Attention at Category- and Item-Level for Micro-Video Click-Through Prediction

This paper investigates how to model user's historical behaviors so as to predict the user's click-through of micro-videos, and proposes a Temporal Hierarchical Attention at Category- and Item-Level (THACIL) network for user behavior modeling.

Routing Micro-videos via A Temporal Graph-guided Recommendation System

This work designs a novel graph-based sequential network to simultaneously model users' dynamic and diverse interest and introduces users' multi-level interest into the recommendation model via a user matrix that is able to learn the enhanced representation of users' interest.

Deep Spatio-Temporal Neural Networks for Click-Through Rate Prediction

The Deep Spatio-Temporal neural Networks (DSTNs) proposed are able to learn the interactions between each type of auxiliary data and the target ad, to emphasize more important hidden information, and to fuse heterogeneous data in a unified framework.

Deep Interest Evolution Network for Click-Through Rate Prediction

This paper proposes a novel model, named Deep Interest Evolution Network~(DIEN), for CTR prediction, which significantly outperforms the state-of-the-art solutions and design interest extractor layer to capture temporal interests from history behavior sequence.

Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction

This work proposes an automated interaction architecture discovering framework for CTR prediction named AutoCTR, which performs evolutionary architecture exploration with learning-to-rank guidance at the architecture level and achieves acceleration using low-fidelity model.

User Behavior Retrieval for Click-Through Rate Prediction

In UBR4CTR, the most relevant and appropriate user behaviors will be firstly retrieved from the entire user history sequence using a learnable search method and fed into a deep model to make the final prediction instead of simply using the most recent ones.

Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction

This paper faces directly the challenge of long sequential user behavior modeling and proposes a novel memory-based architecture named MIMN (Multi-channel user Interest Memory Network) to capture user interests from long sequential behavior data, achieving superior performance over state-of-the-art models.

User Response Learning for Directly Optimizing Campaign Performance in Display Advertising

This paper reformulates a common logistic regression CTR model by putting it back into its subsequent bidding context: rather than minimizing the prediction error, the model parameters are learned directly by optimizing campaign profit.