Inverse Learning with Extremely Sparse Feedback for Recommendation

Guanyu Lin, Yu Zheng, Chen Gao, Jianxin Chang, Yanan Niu, Yang Song, Zhiheng Li, Depeng Jin, Yong Li

Keywords: Recommender System, Unlabeled Data, Denoising Training

Abstract: Negative sampling is widely used in modern recommender systems, where negative data is randomly sampled from the whole item pool. However, such a strategy often introduces false-positive noises. Existing approaches about de-noising recommendation mainly focus on positive instances while ignoring the noise in the large amount of sampled negative feedback. In this paper, we propose a meta learning method to annotate the unlabeled data from loss and gradient perspectives, which considers the noises on both positive and negative instances. Specifically, we first propose $\textit{inverse dual loss}$ (IDL) to boost the true label learning and prevent the false label learning, based on the loss of unlabeled data towards true and false labels during the training process. To achieve more robust sampling on hard instances, we further propose $\textit{inverse gradient}$ (IG) to explore the correct updating gradient and adjust the updating based on meta learning. We conduct extensive experiments on a benchmark and an industrially collected dataset where our proposed method can significantly improve AUC by $9.25\%$ against state-of-the-art methods. Further analysis verifies the proposed inverse learning is model-agnostic and can well annotate the labels combined with different recommendation backbones. The source code along with the best hyper-parameter settings is available at this link: https://anonymous.4open.science/r/InverseLearning-4F4F.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)

TL;DR: We propose inverse learning with inverse dual loss and inverse gradient to annotate the unlabeled data and achieve denoising augmentation from both positive and negative perspectives.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2311.08302/code)