TL;DR
A social relationship adjustment loss function, which dynamically adjusts the weights of social connections, and the Hilbert-Schmidt independence criterion loss function, which reduces the dependence between pre- and post-adjusted user/item embeddings, thereby amplifying the effect of adjusted social relationships on the updated embeddings.
Orthogonal Decomposition for Social Recommendation (ODSR) is proposed, an embedding-space framework that orthogonally decomposes the aggregated social message into an aligned component and an orthogonal deviation, and learns a dimension-wise vector gate to regulate the deviation under ranking supervision.
A novel neural network called the Co-occurrence Graph Neural Network (CoGNN), which utilizes two co-occurrence graphs to establish user and item relationships and outperforms various baseline models in terms of recommendation accuracy and algorithm convergence.
Sequential behaviors and social ties jointly shape user preferences; however, most prior work models them in isolation and relies on shallow fusion in Euclidean space, which struggles to capture temporal drift and hierarchical social structure. We propose a novel framework; HGT4Rec, a Hyperbolic Graph Transformer for Sequential and Social Recommendation. A graph transformer encodes item-transition dependencies to track evolving preferences along the sequence, while a hyperbolic transformer operates on the social graph to represent long-range and hierarchical influence. We further introduce FusionGRU, an adaptive gating module that integrates the two representations into a unified preference state for Top-K prediction. Experiments on Yelp, iFashion, LastFM show that HGT4Rec delivers substantial improvements over the strongest baseline, achieving +348.22% / +314.86%, +383.21% / +210.19%, and +90.85% / +9.83% in Recall@10 and NDCG@10, respectively. Our results demonstrate the value of combining graph transformers with hyperbolic space modeling and the gated fusion for next-item recommendation in sequential and social settings (our code).
Personalisation of product rankings in e-commerce is needed because different users have different interests, demands and browsing conditions. A user-item network model can be employed to represent clicks, favourites, additions to shopping carts, ratings and purchases for personalised Top-k ranking in this paper. This review connects PageRank and Personalised PageRank with graph collaborative filtering, multi-behaviour graph learning, temporal self-supervision and industrial pre-ranking systems. According to the above research, different types of behaviour, the order of interaction and time information, graph construction methods, negative sampling, etc., can affect the ranking results. However, there are still many problems such as scarce and noisy implicit feedback, cold start, popularity bias, preference drift, scalability, privacy, fairness and lack of interpretability. In the future, research will continue to be carried out in the field of combining dynamic heterogeneous graphs, multi-behavioural objectives, causal and self-supervised learning, privacy-preserving computation and graph foundation models. In short, the user-item network model applies linear algebra, probability theory, graph propagation and representation learning to solve the problem of personalised e-commerce ranking. It is convenient to conduct a comparison of the models and decide which one to use.
Recommender systems (RS) are commonly used in areas such as online orders, travel, and music to suggest items that match user interests. With the rapid growth of social interactions and online activity, their use has naturally extended to both personal and Group Recommendation Systems. A group recommender system focuses on providing recommendations based on a group's shared preferences, rather than relying on a single individual’s choices. To overcome these challenges, we propose a novel BADLGRS developed. The GRL model was used to construct a tripartite graph representing interactions between the number of items, users, and group interactions. To effectively capture semantic group features, this phase introduces a novel model, GRUANN. The GCN model with two layers was used to learn user preferences under the GPL. A novel BADLGRS model is evaluated across four datasets and demonstrates superior performance when compared to existing methods. Specifically, it achieves accuracies of 0.893, 0.567, and 0.095, and a MAP of 0.095. Finally, the results of the BADLGRS model consistently outperform existing models in group recommendation tasks.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
