Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph

Togashi, Riku; Otani, Mayu; Satoh, Shin’ichi

doi:10.1145/3437963.3441773

Cited by 37 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MARINE [11] combines homogeneous and heterogeneous graph embedding learning mechanisms to recommend links between entities. Furthermore, KGPL [31] assigns pseudo-positive labels to unobserved samples through knowledge graph neural network-based predictions so that the recommendation model can better deal with the cold-start issues. KGPolicy [40] leverages rich relations between items in the knowledge graphs to sample high-quality negatives and boost the performance of recommenders.…”

Section: Related Workmentioning

confidence: 99%

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings

Hsu

Zhang

2022

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

Sequential recommendation (SR) learns from the temporal dynamics of user-item interactions to predict the next ones. Fairness-aware recommendation mitigates a variety of algorithmic biases in the learning of user preferences. This article aims at bringing a marriage between SR and algorithmic fairness. We propose a novel fairness-aware sequential recommendation task, in which a new metric, interaction fairness , is defined to estimate how recommended items are fairly interacted by users with different protected attribute groups. We propose a multi-task learning-based deep end-to-end model, FairSR, which consists of two parts. One is to learn and distill personalized sequential features from the given user and her item sequence for SR. The other is fairness-aware preference graph embedding (FPGE). The aim of FPGE is two-fold: incorporating the knowledge of users’ and items’ attributes and their correlation into entity representations, and alleviating the unfair distributions of user attributes on items. Extensive experiments conducted on three datasets show FairSR can outperform state-of-the-art SR models in recommendation performance. In addition, the recommended items by FairSR also exhibit promising interaction fairness.

show abstract

Section: Related Workmentioning

confidence: 99%

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings

Hsu

Zhang

2022

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

show abstract

“…In recent years, the prevalent collaborative filtering paradigms have evolved from matrix factorization (MF) to neural networkbased techniques for latent user and item embedding projection, such as Autoencoder-based approaches (e.g., Autorec [28]), attentive CF mechanisms (e.g., ACF [4]), as well as recently developed CF models built upon graph convolutional architectures (e.g., Light-GCN [11]). However, even with the modeling of complex user-item interaction patterns, most CF-based recommendation methods still suffer from the data scarcity issue for users who have not yet interacted with sufficient items [7,14,31]. To overcome such data sparsity problem, Knowledge Graphs (KGs) serving as useful external sources have been incorporated into the recommender system to enhance the user and item representation process, by encoding additional item-wise semantic relatedness [15,39,47].…”

Section: Introductionmentioning

confidence: 99%

Knowledge Graph Contrastive Learning for Recommendation

Yang,

Huang,

Xia

et al. 2022

Preprint

View full text Add to dashboard Cite

Knowledge Graphs (KGs) have been utilized as useful side information to improve recommendation quality. In those recommender systems, knowledge graph information often contains fruitful facts and inherent semantic relatedness among items. However, the success of such methods relies on the high quality knowledge graphs, and may not learn quality representations with two challenges: i) The long-tail distribution of entities results in sparse supervision signals for KG-enhanced item representation; ii) Real-world knowledge graphs are often noisy and contain topic-irrelevant connections between items and entities. Such KG sparsity and noise make the item-entity dependent relations deviate from reflecting their true characteristics, which significantly amplifies the noise effect and hinders the accurate representation of user's preference.To fill this research gap, we design a general Knowledge Graph Contrastive Learning framework (KGCL) that alleviates the information noise for knowledge graph-enhanced recommender systems. Specifically, we propose a knowledge graph augmentation schema to suppress KG noise in information aggregation, and derive more robust knowledge-aware representations for items. In addition, we exploit additional supervision signals from the KG augmentation process to guide a cross-view contrastive learning paradigm, giving a greater role to unbiased user-item interactions in gradient descent and further suppressing the noise. Extensive experiments on three public datasets demonstrate the consistent superiority of our KGCL over state-of-the-art techniques. KGCL also achieves strong performance in recommendation scenarios with sparse user-item interactions, long-tail and noisy KG entities. Our implementation codes are available at https://github.com/yuh-yang/KGCL-SIGIR22. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

“…Despite their effectiveness, we argue that current KGbased methods only focus on improving the recommendation performance from the data level (i.e., leveraging knowledge associations to provide additional semantics beyond collaborative signals), which would inevitably experience a lack of information and poor performance in cold-start scenarios because of overfitting and popularity biases [37], [42]. Take the movie recommendation in Fig.…”

Section: Introductionmentioning

confidence: 99%

“…Challenge I: How to efficiently learn the user preference when evolving the cold-start issues? Existing KG-based recommendations highly rely on the massive user-item feedback, and thus, they suffer from dramatic performance degradation when the user-item interactions are scarce [37], [42]. This implies existing methods can not be directly adopted for our studied cold-start recommendations.…”

Section: Introductionmentioning

confidence: 99%

MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation

Du,

Zhu,

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

A knowledge graph (KG) consists of a set of interconnected typed entities and their attributes. Recently, KGs are popularly used as the auxiliary information to enable more accurate, explainable, and diverse user preference recommendations. Specifically, existing KG-based recommendation methods target modeling high-order relations/dependencies from long connectivity user-item interactions hidden in KG. However, most of them ignore the cold-start problems (i.e., user cold-start and item cold-start) of recommendation analytics, which restricts their performance in scenarios when involving new users or new items. Inspired by the success of meta-learning on scarce training samples, we propose a novel meta-learning based framework called MetaKG, which encompasses a collaborative-aware meta learner and a knowledge-aware meta learner, to capture meta users' preference and entities' knowledge for cold-start recommendations. The collaborative-aware meta learner aims to locally aggregate user preferences for each user preference learning task. In contrast, the knowledge-aware meta learner is to globally generalize knowledge representation across different user preference learning tasks. Guided by two meta learners, MetaKG can effectively capture the high-order collaborative relations and semantic representations, which could be easily adapted to cold-start scenarios. Besides, we devise a novel adaptive task scheduler which can adaptively select the informative tasks for meta learning in order to prevent the model from being corrupted by noisy tasks. Extensive experiments on various cold-start scenarios using three real data sets demonstrate that our presented MetaKG outperforms all the existing state-of-the-art competitors in terms of effectiveness, efficiency, and scalability.

show abstract

Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph

Cited by 37 publications

References 25 publications

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings

Knowledge Graph Contrastive Learning for Recommendation

MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation

Contact Info

Product

Resources

About