Freshness or Accuracy, Why Not Both? Addressing Delayed Feedback via Dynamic Graph Neural Networks

by   Xiaolin Zheng, et al.
Zhejiang University

The delayed feedback problem is one of the most pressing challenges in predicting the conversion rate since users' conversions are always delayed in online commercial systems. Although new data are beneficial for continuous training, without complete feedback information, i.e., conversion labels, training algorithms may suffer from overwhelming fake negatives. Existing methods tend to use multitask learning or design data pipelines to solve the delayed feedback problem. However, these methods have a trade-off between data freshness and label accuracy. In this paper, we propose Delayed Feedback Modeling by Dynamic Graph Neural Network (DGDFEM). It includes three stages, i.e., preparing a data pipeline, building a dynamic graph, and training a CVR prediction model. In the model training, we propose a novel graph convolutional method named HLGCN, which leverages both high-pass and low-pass filters to deal with conversion and non-conversion relationships. The proposed method achieves both data freshness and label accuracy. We conduct extensive experiments on three industry datasets, which validate the consistent superiority of our method.


page 1

page 2

page 3

page 4


Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling

One of the difficulties of conversion rate (CVR) prediction is that the ...

BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network

Graph convolutional networks have achieved great success on graph-struct...

Pre-Training on Dynamic Graph Neural Networks

The pre-training on the graph neural network model can learn the general...

Entire Space Cascade Delayed Feedback Modeling for Effective Conversion Rate Prediction

Conversion rate (CVR) prediction is an essential task for large-scale e-...

A Feedback Shift Correction in Predicting Conversion Rates under Delayed Feedback

In display advertising, predicting the conversion rate, that is, the pro...

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems

Predicting conversion rate (e.g., the probability that a user will purch...

Graph Neural Network-based Surrogate Models for Finite Element Analysis

Current simulation of metal forging processes use advanced finite elemen...

Please sign up or login with your details

Forgot password? Click here to reset