Data-Adaptive Metric Learning with Scale Alignment

With the boosting of neural networks, recommendation methods become significantly improved by their powerful ability of prediction and inference. Existing neural-network based recommender systems (NN-RSs) usually first employ matrix embedding (ME) as a pre-process to learn users' and items' representations (latent vectors), then input these representations to a specific modified neural network framework to make accurate Top-k recommendations. Obviously, the performance of ME has a significant effect on RS models. However, most NN-RSs focus on accuracy by building representations from the direct user-item interactions (e.g., user-item rating matrix), while ignoring the underlying relatedness between users and items (e.g., users who rate the same ratings for the same items should be embedded into similar representations), which is an ideological disadvantage. On the other hand, ME models directly employ inner products as a default loss function metric that cannot project users and items into a proper latent space, which is a methodological disadvantage. In this paper, we propose a supervised collaborative representation learning model -Magnetic Metric Learning (MML) -to map users and items into a unified latent vector space, enhancing the representation learning for NN-RSs. Firstly, MML utilizes dual triplets to model not only the observed relationships between users and items, but also the underlying relationships between users as well as items to overcome the ideological disadvantage. Specifically, a modified metric-based dual loss function is proposed in MML to gather similar entities and disperse the dissimilar ones. With MML, we can easily compare all the relationships (user to user, item to item, user to item) according to the weighted metric, which overcomes the methodological disadvantage. We conduct extensive experiments on four real-world datasets with large item space. The results demonstrate that MML can learn a proper unified latent space for representations from the user-item matrix with high accuracy and effectiveness, and lead to a performance gain over the state-of-the-art RS models by an average of 17%.

show abstract

“…Metric learning (ML) is a research spot for image recognition, clustering, and recommendation system [16,[42][43][44][45][46].…”

Section: Metric Learning (Ml)mentioning

confidence: 99%

A Unified Collaborative Representation Learning for Neural-Network Based Recommender Systems

Wang

Yang

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…The application scenarios where SBIR is feasible are closer to the zero-shot setting, requiring the training and testing categories to be non-overlapping. ZS-SBIR (Yelamarthi et al 2018;Liu et al 2019;Tian et al 2022;Sain et al 2023;Lin et al 2023), which combines zero-shot learning (Lampert, Nickisch, and Harmeling 2013; Xian et al 2018;Chen et al 2019;Yan et al 2022) and SBIR as a single task, has become a research problem that has garnered increased attention recently. These works leverage labeled data and external auxiliary knowledge to achieve cross-category adaptation between sketches and images.…”

Section: Introductionmentioning

confidence: 99%

Asymmetric Mutual Alignment for Unsupervised Zero-Shot Sketch-Based Image Retrieval

Yin,

Yan,

et al. 2024

AAAI

View full text Add to dashboard Cite

In recent years, many methods have been proposed to address the zero-shot sketch-based image retrieval (ZS-SBIR) task, which is a practical problem in many applications. However, in real-world scenarios, on the one hand, we can not obtain training data with the same distribution as the test data, and on the other hand, the labels of training data are not available as usual. To tackle this issue, we focus on a new problem, namely unsupervised zero-shot sketch-based image retrieval (UZS-SBIR), where the available training data does not have labels while the training and testing categories are not overlapping. In this paper, we introduce a new asymmetric mutual alignment method (AMA) including a self-distillation module and a cross-modality mutual alignment module. First, we conduct self-distillation to extract the feature embeddings from unlabeled data. Due to the lack of available information in an unsupervised manner, we employ the cross-modality mutual alignment module to further excavate underlying intra-modality and inter-modality relationships from unlabeled data, and take full advantage of these correlations to align the feature embeddings in image and sketch domains. Meanwhile, the feature representations are enhanced by the intra-modality clustering relations, leading to better generalization ability to unseen classes. Moreover, we conduct an asymmetric strategy to update the teacher and student networks, respectively. Extensive experimental results on several benchmark datasets demonstrate the superiority of our method.

show abstract

Boundary-restricted metric learning

Chen,

Gong,

et al. 2023

Mach Learn

View full text Add to dashboard Cite

Data-Adaptive Metric Learning with Scale Alignment

Cited by 4 publications

References 18 publications

A Unified Collaborative Representation Learning for Neural-Network Based Recommender Systems

A Unified Collaborative Representation Learning for Neural-Network Based Recommender Systems

Asymmetric Mutual Alignment for Unsupervised Zero-Shot Sketch-Based Image Retrieval

Boundary-restricted metric learning

Contact Info

Product

Resources

About