Dynamic Graph Learning to Denoise Implicit Feedback for Graph Collaborative Filtering

E-commerce platforms usually train their recommender system models to achieve personalized recommendations based on user behavior data. User behavior can be categorized into implicit and explicit feedback. Explicit feedback data have been well studied. However, the implicit feedback data still have many issues, such as the multiple types of behavior data, lack of negative feedback, and lack of the ability to express the real user preference. Targeting these problems of implicit feedback, we propose a TDF-WNSP-WLFM (time decay factor-weight of negative sample possibility-weighted latent factor model) based on the latent factor model for product recommendation. Our method mainly focuses on reconstructing the implicit rating matrix to enable the algorithm to perform better. The TDF-WNSP-WLFM algorithm is tested on two public user behavior datasets from Taobao and REES46, two big e-commerce platforms. Our algorithm compares favorably with other known collaborative filtering methods.

Sequential recommendation models aim to predict the interested items to a user based on his historical behaviors. To train sequential recommenders, implicit feedback data is widely adopted since it is easier to obtain than explicit feedback data. In the setting of implicit feedback, a user’s historical behaviors can be characterized as a chronologically ordered sequence of interacted items. From a perspective of machine learning, the historical interaction sequence and the recommended items can be considered as context and label , respectively, which are usually in one-hot representations in the recommendation models. However, due to the discrete nature, one-hot representations are hard to sufficiently reflect the underlying user preference, and might also contain noise from implicit feedback that will mislead the model training. To solve these issues, we propose a general optimization framework, Multi-View Smoothness (MVS), to enhance the smoothness of sequential recommendation models in both data representations and model learning. Specifically, with the help of a complementary model, we smooth and enrich the one-hot representations of contexts and labels to better depict the underlying user preference (i.e., context smoothness and label smoothness), and devise a model regularization strategy to enforce the neighborhood smoothness of the model itself (i.e., model smoothness). Based on these strategies, we design three regularizers to constrain and improve the training of sequential recommendation models. Extensive experiments on five datasets show that our approach is able to improve the performance of various base models consistently and outperform other regularization training methods.

Farfetch is the leading platform for online luxury fashion shopping. We have more than 3000 brands and high-end designers with the biggest catalog of luxury products available worldwide to more than 1 million customers.

In the recommendation system, compared with the explicit feedback, implicit feedback has the characteristics of large quantity, easier tracking and easier access. Even in many practical application scenarios of the recommendation system, there is only implicit feedback without explicit feedback Based on implicit feedback to recommend there has been a problem, that is usually implicit feedback provides only reflect the noise signal of user preferences, because although the observed interactions at least reflect the user’s interest in the item, but not observed the interaction may be missing data, and is not necessarily negative samples, so it’s natural lack of negative feedback In this work, this paper improves the neural colla-borative filtering algorithm (NCF) by extracting the popularity characteristics as the basis for extracting negative samples from implicit feedback data. To a certain extent, it solves the problem that negative sampling introduces a lot of noise in previous work. At the same time, we found that the gradient vanishing in the training process when using the traditional loss function Binary Cross Entropy (BCE). In order to solve this problem, a new loss function, BCE-Max, was proposed in this paper. Based on the above improvements, we proposed a neural collaborative filtering recommendation algorithm (PNCF) based on popularity characteristics. By comparing the performance of PNCF, NCF, traditional collaborative filtering and some matrix factorization recommendation algorithms in the evaluation indexes such as HR@10, NDCG@10 and avg_popularity@10, we find that PNCF has certain advantages over these recommendation algorithms. Meanwhile, We found that compared with NCF, the experimental results of PNCF improved by about 1.2% and 2% onHR@10 and NDCG@10 respectively, and even improved by about 2% on HR@1 and NDCG@I.

Collaborative Filtering with Implicit Feedbacks e.g., browsing or clicking records, named as CF-IF, is demonstrated to be an effective way in recommender systems. Existing works of CF-IF can be mainly classified into two categories, i.e., point-wise regression based and pair-wise ranking based, where the latter one relaxes assumption and usually obtains better performance in empirical studies. In real applications, implicit feedback is often very sparse, causing CF-IF based methods to degrade significantly in recommendation performance. In this case, side information e.g., item content is usually introduced and utilized to address the data sparsity problem. Nevertheless, the latent feature representation learned from side information by topic model may not be very effective when the data is too sparse. To address this problem, we propose collaborative deep ranking CDR, a hybrid pair-wise approach with implicit feedback, which leverages deep feature representation of item content into Bayesian framework of pair-wise ranking model in this paper. The experimental analysis on a real-world dataset shows CDR outperforms three state-of-art methods in terms of recall metric under different sparsity level.

Ranking algorithms in recommender systems influence people to make decisions. Conventional ranking algorithms based on implicit feedback data aim to maximize the utility to users by capturing users’ preferences over items. However, these utility-focused algorithms tend to cause fairness issues that require careful consideration in online platforms. Existing fairness-focused studies does not explicitly consider the problem of lacking negative feedback in implicit feedback data, while previous utility-focused methods ignore the importance of fairness in recommendations. To fill this gap, we propose a Generative Adversarial Networks (GANs) based learning algorithm FairGAN mapping the exposure fairness issue to the problem of negative preferences in implicit feedback data. FairGAN does not explicitly treat unobserved interactions as negative, but instead, adopts a novel fairness-aware learning strategy to dynamically generate fairness signals. This optimizes the search direction to make FairGAN capable of searching the space of the optimal ranking that can fairly allocate exposure to individual items while preserving users’ utilities as high as possible.

In this era of exponential growth in the scale of data, information overload has become an urgent problem, and the use of increasingly flexible sensor cloud systems (SCS) for data collection has become a mainstream trend. Recommendation algorithms can search massive data sets to uncover information that meets the needs of users based on their interests. To improve the accuracy of recommendation scoring, this article proposes a score prediction algorithm that combines deep learning and matrix factorization. To address the problem of sparse scoring data, our study employs a sensor cloud system to collect data information, preprocesses the collected information, and then uses a deep learning model combined with explicit and implicit feedback to generate recommendations. The proposed algorithm, MF-NeuRec, combines fusion matrix decomposition and the NeuRec model score prediction algorithm. The algorithm employs user-based and item-based NeuRec algorithms to extract the feature vectors of users and items under implicit feedback data. The obtained user and item feature vectors are integrated in a certain ratio through the use of matrix decomposition under the display feedback data. The user and item feature vectors obtained by the algorithm are merged and analyzed to predict how users will rate items. Experiments demonstrate that the algorithm can improve the accuracy of recommendations.

Traditional teaching course recommendation methods mainly rely on user satisfaction or utility evaluation of courses. In web front-end teaching course recommendation, the personalized learning needs of users are ignored, resulting in poor quality of recommended courses. Therefore, to solve the problem of personalized course recommendation, this paper proposes a personalized course recommendation method based on implicit feedback. This method is based on user interaction behavior analysis, implicit feedback data is collected, including multidimensional data such as browsing history, click behavior, and dwell time, and stored in a relational database. Extract user learning features and group user browsing records to discover user groups with similar browsing behaviors. Build a knowledge graph for web-based teaching courses, combined with user interest models, integrate course knowledge points, associations, etc. into recommendation methods, generate personalized recommendation lists, and this approach effectively enhances recommendation accuracy and diversity. To verify the performance of the proposed recommendation method, a control group was set up to conduct comparative analysis based on indicators such as recommendation novelty, recommendation coverage, and normalized cumulative loss gain (NDCG). Experimental results demonstrate the novelty and coverage of recommendations are much higher than traditional methods, and it can cover a wider range of courses. Meanwhile, as the length of the recommendation list increases, the NDCG value maintains a stable growth, proving that this method can more accurately capture user interests and generate high-quality personalized recommendation lists. In future research, the sample size will be expanded to more comprehensively validate the effectiveness of recommendation methods in different user groups.

Enhancing robustness in implicit feedback recommender systems with subgraph contrastive learning

Distinguishing latent interaction types from implicit feedbacks for recommendation

The acquisition of explicit user feedback (e.g., ratings) in real-world recommender systems is often hindered by the need for active user involvement. To mitigate this issue, implicit feedback (e.g., clicks) generated during user browsing is exploited as a viable substitute. However, implicit feedback possesses a high degree of noise, which significantly undermines recommendation quality. While many methods have been proposed to address this issue by assigning varying weights to implicit feedback, two shortcomings persist: (1) the weight calculation in these methods is iteration-independent, without considering the influence of weights in previous iterations, and (2) the weight calculation often relies on prior knowledge, which may not always be readily available or universally applicable.

Reorganizing implicit feedback of users as a user-item interaction graph facilitates the applications of graph convolutional networks (GCNs) in recommendation tasks. In the interaction graph, edges between user and item nodes function as the main element of GCNs to perform information propagation and generate informative representations. Nevertheless, an underlying challenge lies in the quality of interaction graph, since observed interactions with less-interested items occur in implicit feedback (say, a user views micro-videos accidentally). This means that the neighborhoods involved with such false-positive edges will be influenced negatively and the signal on user preference can be severely contaminated. However, existing GCN-based recommender models leave such challenge under-explored, resulting in suboptimal representations and performance. In this work, we focus on adaptively refining the structure of interaction graph to discover and prune potential false-positive edges. Towards this end, we devise a new GCN-based recommender model, Graph-Refined Convolutional Network (GRCN), which adjusts the structure of interaction graph adaptively based on status of model training, instead of remaining the fixed structure. In particular, a graph refining layer is designed to identify the noisy edges with the high confidence of being false-positive interactions, and consequently prune them in a soft manner. We then apply a graph convolutional layer on the refined graph to distill informative signals on user preference. Through extensive experiments on three datasets for micro-video recommendation, we validate the rationality and effectiveness of our GRCN. Further in-depth analysis presents how the refined graph benefits the GCN-based recommender model.

Mixed similarity learning for recommendation with implicit feedback

Social online learning is gaining prominence with the emergence of social media and networks. In the presence of recommendation systems, the learner has access to several educational contents and elements proposed according to his interaction, profile, dynamics and other parameters. Our proposal revolves around an intelligent recommender system for generating recommendations in social learning environments, in particular social networks, based on the learner's activities, falling into the category of hybrid recommender systems and integrating the concept of community detection in the generation of recommendations. The proposed global approach is composed of several recommender systems: the correlation and co-occurrence based recommender system aims at measuring the degree of connectivity between learners' activities in order to generate relevant recommendations in the light of learners' implicit feedback, the community detection based recommender system through friendships. This system is an important part of our overall approach as it combines the hybrid recommendation system with the community detection based on friendship links between learners and the recommendation system based on the degree of interactivity of learners with the available learning objects. This system also consists in detecting communities, which group learners with similar preferences and orientations. The results obtained prove the potential of combining the two notions of connectivity and the integration of community detection based on several indicators to produce more relevant recommendations, while offering recommendations by group of learners by applying the concept of continuous improvement.KeywordsSocial learningRecommender systemCorrelationCo-occurrenceFriendshipInteractionCommunity detection

Graph Collaborative Filtering (GCF) methods have emerged as an effective recommendation approach, capturing users’ preferences over items by modeling user–item interaction graphs. However, these methods suffer from data sparsity in real scenarios, and their performance can be improved using contrastive learning. In this paper, we propose an optimized method, named LoRA-NCL, for GCF based on Neighborhood-enriched Contrastive Learning (NCL) and low-rank dimensionality reduction. We incorporate low-rank features obtained through matrix factorization into the NCL framework and employ LightGCN to extract high-dimensional representations. Extensive experiments on five public datasets demonstrate that the proposed method outperforms a competitive graph collaborative filtering base model, achieving 4.6% performance gains on the MovieLens dataset, respectively.