User Item Similarity Research Articles

Simplify to the Limit! Embedding-less Graph Collaborative Filtering for Recommender Systems

The tremendous positive driving effect of Graph Convolutional Network (GCN) and Graph Contrastive Learning (GCL) for recommender systems has become a consensus. GCN encoders are extensively used in recommendation models for capturing high-order connectivities between users and items, whereas GCL accelerates the training of recommendation tasks by adding extra supervision signals from contrastive objectives. However, little attention has been paid on corresponding theories that are truly tailored to recommendation tasks. From the technical perspective, Collaborative Filtering (CF) is seen as an important factor in recommender systems. It is applied to measure user-user, item-item, and user-item similarities rather than to achieve better clustering or node classification results. Besides, heuristic-based data augmentation may not be hold true in the field of recommender systems as it requires additional training costs and introduces noises that will corrupt the interaction graph structure and the semantic information of nodes. To tackle these limitations, we propose a novel Embedding-less Graph Collaborative Filtering (EGCF) for recommendation, which is tailor-made for the problem mentioned for CF and further simplifies existing solutions. Structurally, it consists of two parts: embedding-less GCN and embedding-less GCL. The former improves user-item affinity by streamlining user-type embeddings and carrying out iterative graph convolution. And the latter utilizes three-type contrastive objectives to directly measure the alignment and the uniformity of users, items, and interaction pairs, respectively, avoiding any type of data augmentation or multi-view construction. Even though EGCF has been extremely streamlined, extensive experimental results on three classical datasets demonstrate the effectiveness of EGCF in terms of recommendation accuracy and training efficiency. The code and used datasets are released at https://github.com/BlueGhostYi/ID-GRec.

Incorporating User Item Similarity in Hybrid Neighborhood-Based Recommendation Systems

Recommendation systems have been developed in many domains to help users with information overload from the large volume of online multimedia content by providing them with appropriate options. Recently developed hybrid recommendation systems require a large amount of data to understand users’ interests and give appropriate suggestions. However, several internet privacy issues make users skeptical about sharing their personal information with online service providers, limiting the potential of these systems. The study in this paper introduces various novel methods utilizing the baseline estimate to learn user interests in specific item features from their past interactions. Subsequently, extracted user feature vectors are implemented to estimate the user-item correlations, providing an additional fine-tuning factor for neighborhood-based collaborative filtering systems. Comprehensive experiments show that utilizing the user-item similarity scores in the rating prediction task can improve the accuracy of hybrid neighborhood-based systems by at least 2.11% compared to traditional methods while minimizing the need for tracking users' digital footprints.

Side Information Fusion for Recommender Systems over Heterogeneous Information Network

Collaborative filtering (CF) has been one of the most important and popular recommendation methods, which aims at predicting users’ preferences (ratings) based on their past behaviors. Recently, various types of side information beyond the explicit ratings users give to items, such as social connections among users and metadata of items, have been introduced into CF and shown to be useful for improving recommendation performance. However, previous works process different types of information separately, thus failing to capture the correlations that might exist across them. To address this problem, in this work, we study the application of heterogeneous information network (HIN), which offers a unifying and flexible representation of different types of side information, to enhance CF-based recommendation methods. However, we face challenging issues in HIN-based recommendation, i.e., how to capture similarities of complex semantics between users and items in a HIN, and how to effectively fuse these similarities to improve final recommendation performance. To address these issues, we apply metagraph to similarity computation and solve the information fusion problem with a “matrix factorization (MF) + factorization machine (FM)” framework. For the MF part, we obtain the user-item similarity matrix from each metagraph and then apply low-rank matrix approximation to obtain latent features for both users and items. For the FM part, we apply FM with Group lasso (FMG) on the features obtained from the MF part to train the recommending model and, at the same time, identify the useful metagraphs. Besides FMG, a two-stage method, we further propose an end-to-end method, hierarchical attention fusing, to fuse metagraph-based similarities for the final recommendation. Experimental results on four large real-world datasets show that the two proposed frameworks significantly outperform existing state-of-the-art methods in terms of recommendation performance.

Improved Metric-Based Recommender by Historical Interactions

A remarkable success in recommendations has been achieved by using methods based on metric learning, especially in digital marketing. However, the existing methods do not consider the relative preferences among items that users like. To overcome this issue, we propose an improved recommender model. First, the model analyses the user-item bipartite graph from historical interactions, and collects user-item similarities based on the topological features from this graph. Then, similar to other metric-based methods, both users and items are embedded as latent positions in a low-dimensional space, where users’ preferences on items are modelled as distances. Thus, we propose an improved metric-based recommender, i.e. the Graph Embedded Metric Factorisation recommender, under the assumptions that (1) the distance between a target user and an interacted-with item is determined by their topological similarity, and (2) for a target user, non-interacted items are located farther away than interacted-with ones. Comprehensive experiments on three practical datasets were implemented. Empirical results indicate that our improved recommender outperforms current state-of-the-art methods when making personalised recommendations based on users’ implicit feedback.

Neural Binary Representation Learning for Large-Scale Collaborative Filtering

Integrating hashing into collaborative filtering (CF) has been a promising solution to address the efficiency problem of large-scale recommender systems, i.e., hashing users and items into binary codes and then making recommendations in Hamming space. However, most of the existing hashing methods for CF solely focus on modeling the user-item similarity (a.k.a. preference) but omit the user-user and item-item similarities, which cannot well preserve the original geometry in the vector space. Another tough issue is how to effectively tackle the encoding loss from the continuous vector space to the discrete Hamming space. In this paper, we propose a neural binary representation (NBR) learning approach by combining hashing with a neural network for the large-scale CF tasks. Our NBR problem is formulated as a Hamming similarity loss plus two anchor smoothing terms, which jointly preserve the intrinsic user-item, user-user, and item-item similarities. To compensate the encoding loss introduced by hashing, the anchors for users and items are pre-learned using both user-item interactions and the side-information of users and items through an AutoEncoder model. In particular, to solve the NBR problem, we develop a computationally efficient algorithm, which learns the binary codes in a fast bit-by-bit way and achieves less quantization deviation than the conventional CF hashing schemes. The extensive experiments on three benchmarks validate the superiority of our NBR approach in comparison to the state-of-the-art CF hashing methods.

Personalized recommendation algorithm based on preference features

A hybrid collaborative filtering algorithm based on the user preferences and item features is proposed. A thorough investigation of Collaborative Filtering (CF) techniques preceded the development of this algorithm. The proposed algorithm improved the user-item similarity approach by extracting the item feature and applying various item features' weight to the item to confirm different item features. User preferences for different item features were obtained by employing user evaluations of the items. It is expected that providing better recommendations according to preferences and features would improve the accuracy and efficiency of recommendations and also make it easier to deal with the data sparsity. In addition, it is expected that the potential semantics of the user evaluation model would be revealed. This would explain the recommendation results and increase accuracy. A portion of the MovieLens database was used to conduct a comparative experiment among the proposed algorithms, i.e., the collaborative filtering algorithm based on the item and the collaborative filtering algorithm based on the item feature. The Mean Absolute Error (MAE) was utilized to conduct performance testing. The experimental results show that employing the proposed personalized recommendation algorithm based on the preference-feature would significantly improve the accuracy of evaluation predictions compared to two previous approaches.

SOCIAL INTEREST FOR USER SELECTING ITEMS IN RECOMMENDER SYSTEMS

Recommender systems have developed rapidly and successfully. The system aims to help users find relevant items from a potentially overwhelming set of choices. However, most of the existing recommender algorithms focused on the traditional user-item similarity computation, other than incorporating the social interests into the recommender systems. As we know, each user has their own preference field, they may influence their friends' preference in their expert field when considering the social interest on their friends' item collecting. In order to model this social interest, in this paper, we proposed a simple method to compute users' social interest on the specific items in the recommender systems, and then integrate this social interest with similarity preference. The experimental results on two real-world datasets Epinions and Friendfeed show that this method can significantly improve not only the algorithmic precision-accuracy but also the diversity-accuracy.