ProtoCF: Prototypical collaborative filtering for few-shot recommendation

Aravind Sankar, Junting Wang, Adit Krishnan, Hari Sundaram

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In recent times, deep learning methods have supplanted conventional collaborative filtering approaches as the backbone of modern recommender systems. However, their gains are skewed towards popular items with a drastic performance drop for the vast collection of long-tail items with sparse interactions. Moreover, we empirically show that prior neural recommenders lack the resolution power to accurately rank relevant items within the long-tail. In this paper, we formulate long-tail item recommendations as a few-shot learning problem of learning-to-recommend few-shot items with very few interactions. We propose a novel meta-learning framework ProtoCF that learns-to-compose robust prototype representations for few-shot items. ProtoCF utilizes episodic few-shot learning to extract meta-knowledge across a collection of diverse meta-training tasks designed to mimic item ranking within the tail. To further enhance discriminative power, we propose a novel architecture-agnostic technique based on knowledge distillation to extract, relate, and transfer knowledge from neural base recommenders. Our experimental results demonstrate that ProtoCF consistently outperforms state-of-art approaches on overall recommendation (by 5% Recall@50) while achieving significant gains (of 60-80% Recall@50) for tail items with less than 20 interactions.

Original languageEnglish (US)
Title of host publicationRecSys 2021 - 15th ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery
Number of pages10
ISBN (Electronic)9781450384582
StatePublished - Sep 13 2021
Event15th ACM Conference on Recommender Systems, RecSys 2021 - Virtual, Online, Netherlands
Duration: Sep 27 2021Oct 1 2021

Publication series

NameRecSys 2021 - 15th ACM Conference on Recommender Systems


Conference15th ACM Conference on Recommender Systems, RecSys 2021
CityVirtual, Online


  • Collaborative Filtering
  • Few-shot learning
  • Meta Learning
  • Recommendation System

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Networks and Communications
  • Hardware and Architecture


Dive into the research topics of 'ProtoCF: Prototypical collaborative filtering for few-shot recommendation'. Together they form a unique fingerprint.

Cite this