Differentiable Neural Input Search for Recommender Systems Article Swipe

MAKE IMPACT

Weiyu Cheng , Yanyan Shen , Linpeng Huang · YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2006.04466

Latent factor models are the driving forces of the state-of-the-art recommender systems, with an important insight of vectorizing raw input features into dense embeddings. The dimensions of different feature embeddings are often set to a same value empirically, which limits the predictive performance of latent factor models. Existing works have proposed heuristic or reinforcement learning-based methods to search for mixed feature embedding dimensions. For efficiency concern, these methods typically choose embedding dimensions from a restricted set of candidate dimensions. However, this restriction will hurt the flexibility of dimension selection, leading to suboptimal performance of search results. In this paper, we propose Differentiable Neural Input Search (DNIS), a method that searches for mixed feature embedding dimensions in a more flexible space through continuous relaxation and differentiable optimization. The key idea is to introduce a soft selection layer that controls the significance of each embedding dimension, and optimize this layer according to model's validation performance. DNIS is model-agnostic and thus can be seamlessly incorporated with existing latent factor models for recommendation. We conduct experiments with various architectures of latent factor models on three public real-world datasets for rating prediction, Click-Through-Rate (CTR) prediction, and top-k item recommendation. The results demonstrate that our method achieves the best predictive performance compared with existing neural input search approaches with fewer embedding parameters and less time cost.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2006.04466

PDF

https://arxiv.org/pdf/2006.04466

OA Status

green

Cited By

20

References

40

Related Works

10

OpenAlex ID

https://openalex.org/W3033138048

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W3033138048

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2006.04466

Digital Object Identifier

Title

Differentiable Neural Input Search for Recommender Systems

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2020

Year of publication

Publication date

2020-06-08

Full publication date if available

Authors

Weiyu Cheng, Yanyan Shen, Linpeng Huang

List of authors in order

Landing page

https://arxiv.org/abs/2006.04466

Publisher landing page

PDF URL

https://arxiv.org/pdf/2006.04466

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2006.04466

Direct OA link when available

Concepts

Computer science, Embedding, Recommender system, Artificial intelligence, Feature (linguistics), Heuristic, Feature engineering, Dimension (graph theory), Machine learning, Set (abstract data type), Feature vector, Differentiable function, Key (lock), Data mining, Deep learning, Mathematics, Linguistics, Pure mathematics, Philosophy, Computer security, Programming language, Mathematical analysis

Top concepts (fields/topics) attached by OpenAlex

Cited by

20

Total citation count in OpenAlex

Citations by year (recent)

2024: 1, 2023: 5, 2022: 4, 2021: 7, 2020: 3

Per-year citation counts (last 5 years)

References (count)

40

Number of works referenced by this work

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload