Unbiased learning to rank algorithm based on VS-GAN

The goal of unbiased learning to rank is to utilize noisy click data to generate more accurate rankings for candidate items. This approach aims to eliminate biases introduced by user click preferences, allowing the ranking model to better reflect true user intent and content relevance. In addressing the task of unbiased learning to rank, most existing models directly use click signals as indicators of relevance and examination propensity, neglecting the uncertainty in user clicks. Such uncertain click signals often interfere with the performance of unbiased learning to rank models, causing the final ranking results to still contain some degree of bias. To address this issue, we propose an unbiased learning to rank algorithm based on VS-GAN. We formulate the task as a semi-supervised learning problem with missing labels and leverage adversarial training in a GAN network to eliminate the uncertainty in click data. We introduce Variational Autoencoders (VAE) and residual connections into the generator to construct a novel generator network. The generator samples from a combination of uncertain and real clicks from the discriminator, while the discriminator challenges the generator in an adversarial training process to achieve better performance. Additionally, in the debiasing process, we incorporate position factors into a pairwise debiasing method to generate unbiased labels from the discriminator to the generator more effectively. Experimental results demonstrate that our algorithm exhibits superior performance on the dataset, providing a new perspective for unbiased learning to rank.