Denoising Implicit Feedback for Recommendation

By Wenjie Wang, Fuli Feng, Xiangnan He, Liqiang Nie, Tat-seng Chua. Web Search and Data Mining, 2020

334 citations recorded by the source corpus.

The ubiquity of implicit feedback makes them the default choice to build online recommender systems. While the large volume of implicit feedback alleviates the data sparsity issue, the downside is that they are not as clean in reflecting the actual satisfaction of users. For example, in E-commerce, a large portion of clicks do not translate to purchases, and many purchases end up with negative reviews. As such, it is of critical importance to account for the inevitable noises in implicit feedback for recommender training. However, little work on recommendation has taken the noisy nature of implicit feedback into consideration. In this work, we explore the central theme of denoising implicit feedback for recommender training. We find serious negative impacts of noisy implicit feedback, i.e., fitting the noisy data hinders the recommender from learning the actual user preference. Our target is to identify and prune the noisy interactions, so as to improve the efficacy of recommender training. By observing the process of normal recommender training, we find that noisy feedback typically has large loss values in the early stages. Inspired by this observation, we propose a new training strategy named Adaptive Denoising Training (ADT), which adaptively prunes noisy interactions during training. Specifically, we devise two paradigms for adaptive loss formulation: Truncated Loss that discards the large-loss samples with a dynamic threshold in each iteration; and Reweighted Loss that adaptively lowers the weights of large-loss samples. We instantiate the two paradigms on the widely used binary cross-entropy loss and test the proposed ADT strategies on three representative recommenders. Extensive experiments on three benchmarks demonstrate that ADT significantly improves the quality of recommendation over normal training.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/374f36c9081ab5dc686ab833c42a7297235cd13f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Management Science and Operations Research

Citations in the corpus

Advances and Challenges in Conversational Recommender Systems: A Survey (2021, positive): “First, users might not like the items they chose, as they may make wrong decisions [216, 217].”
Self-supervised Graph Learning for Recommendation (2020, background): “, a user is misled to click an item and finds it uninteresting after consuming it [44].”
Diffusion Recommender Model (2023, methodology): “naturally noisy due to false-positive and false-negative interactions [38, 39, 41] and 2) retaining personalized information, we reduce the added noises in the forward process by setting T ′ < T .”
Representation Learning with Large Language Models for Recommendation (2023, background): “Furthermore, it is worth noting that a substantial portion of the data in these graph-based recommenders consists of implicit feedback [27, 33], which can introduce noise from false negatives or bias ( e . g ., misclicks [34] or popularity bias [5]).”
A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation (2022, background): “The former work [15, 22, 23, 27] leverages attention mechanisms or pre-defined functions to calculate a node’s attention or affinity scores with its neighbors.”
LLMRec: Large Language Models with Graph Augmentation for Recommendation (2023, background): “…u-i interactions, which encompass items that were not genuinely intended by the user, such as accidental clicks or instances influenced by popularity bias [31]; (ii) false negative represented by non-interacted items, which may not necessarily indicate user dispreference but are…”