AI Chat AI Image Generator AI Video Text to Speech

"Does it come in black?" CLIP-like models are zero-shot recommenders

04/05/2022

∙

by Patrick John Chia, et al.

∙

∙

Product discovery is a crucial component for online shopping. However, item-to-item recommendations today do not allow users to explore changes along selected dimensions: given a query item, can a model suggest something similar but in a different color? We consider item recommendations of the comparative nature (e.g. "something darker") and show how CLIP-based models can support this use case in a zero-shot manner. Leveraging a large model built for fashion, we introduce GradREC and its industry potential, and offer a first rounded assessment of its strength and weaknesses.

Patrick John Chia
7 publications
Jacopo Tagliabue
26 publications
Federico Bianchi
34 publications
Ciro Greco
14 publications
Diogo Goncalves
2 publications

page 1

page 2

page 3

page 4

research

∙ 07/26/2023

Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences

Traditional recommender systems leverage users' item preference history ...

0 Scott Sanner, et al. ∙

research

∙ 05/12/2023

Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Training

Existing recommender systems face difficulties with zero-shot items, i.e...

0 Ziwei Fan, et al. ∙

research

∙ 01/03/2022

Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction

In this paper, we introduce zero-shot cost models which enable learned c...

0 Benjamin Hilprecht, et al. ∙

research

∙ 08/31/2021

Zero Shot on the Cold-Start Problem: Model-Agnostic Interest Learning for Recommender Systems

User behavior has been validated to be effective in revealing personaliz...

7 Philip J. Feng, et al. ∙

research

∙ 05/18/2021

Zero-Shot Recommender Systems

Performance of recommender systems (RS) relies heavily on the amount of ...

49 Hao Ding, et al. ∙

research

∙ 05/10/2023

Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction

Large Language Models (LLMs) have demonstrated exceptional capabilities ...

0 Wang-Cheng Kang, et al. ∙

research

∙ 04/29/2018

CRAFT: Complementary Recommendations Using Adversarial Feature Transformer

Traditional approaches for complementary product recommendations rely on...

0 Cong Phuoc Huynh, et al. ∙