Meta-Prod2Vec: Product Embeddings Using Side-Information for Recommendation

By Flavian Vasile, Elena Smirnova, Alexis Conneau. 2016

273 citations recorded by the source corpus.

We propose Meta-Prod2vec, a novel method to compute item similarities for recommendation that leverages existing item metadata. Such scenarios are frequently encountered in applications such as content recommendation, ad targeting and web search. Our method leverages past user interactions with items and their attributes to compute low-dimensional embeddings of items. Specifically, the item metadata is injected into the model as side information to regularize the item embeddings. We show that the new item representations lead to better performance on recommendation tasks on an open music dataset.

Subfields: Artificial Intelligence, Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Signal Processing

Citations in the corpus

Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks (2017, methodology): “The first type of methods includes factor models that learn a low-rank decomposition of sparse user-item interactions matrix [3, 12, 21].”
Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks (2017, methodology): “In [4, 34], items’ meta-data are modeled to improve the recommendation task.”
Recommender Systems in the Era of Large Language Models (LLMs) (2023, unknown): “Thus , the user may want to watch the recommended new movie. items, such as user demographics or item descriptions, to enhance user and item representations for improving recommendation performance [27].”
Are we really making much progress? A worrying analysis of recent neural recommendation approaches (2019, unknown): “Non-reproducible: KDD: [43], RecSys: [41], [6], [38], [44], [21], [45], SIGIR: [32], [7], WWW: [42], [11]”
Sequence-Aware Recommender Systems (2018, methodology): “Distributional embeddings [9, 27, 37, 92, 103, 108, 124] Supervised models w/sliding window [9, 110, 126]”
Causal embeddings for recommendation (2017, background): “We can separate the newly proposed solutions in two main types of approaches, ones that learn item embeddings that optimize for item-item similarity prediction ([7, 16, 24]) and the ones that learn user sequence embeddings to optimize for next item prediction ([8, 9]).”
A Survey on Session-based Recommender Systems (2019, background): “[117] designed a shallow network to embed the ID and features of each item simultaneously to build a compound item representation to tackle the cold-start item issues; some similar works include [107, 110].”
Evaluation of session-based recommendation algorithms (2018, background): “2013] or distributional embeddings [Baeza-Yates et al. 2015; Djuric et al. 2014; Grbovic et al. 2015; Reddy et al. 2016; Tagami et al. 2015; Vasile et al. 2016; Zheleva et al. 2010].”