mlsanityData to 7 Oct 2026

MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning

arXiv 2203.04540 ↗First posted 9 Mar 2022cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate understanding of users in terms of predicative segments play an essential role in the day to day operation of modern internet enterprises. Nevertheless, there are significant challenges that limit the quality of data, especially on long tail predictive tasks. In this work, we present MetaCon, our unified predicative segments system with scalable, trillion concepts meta learning that addresses these challenges. It builds on top of a flat concept representation that summarizes entities' heterogeneous digital footprint, jointly considers the entire spectrum of predicative tasks as a single learning task, and leverages principled meta learning approach with efficient first order meta-optimization procedure under a provable performance guarantee in order to solve the learning task. Experiments on both proprietary production datasets and public structured learning tasks demonstrate that MetaCon can lead to substantial improvements over state of the art recommendation and ranking approaches.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 66 references that are in the map. First posted on arXiv 9 Mar 2022.

Builds on

18 of 66 references.

References · 18

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  4. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  5. 2016Wide & Deep Learning for Recommender Systemscited by 745
  6. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  7. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
  8. 2019Meta-Learning with Implicit Gradientscited by 523
  9. 2018Bilevel Programming for Hyperparameter Optimization and Meta-Learningcited by 403
  10. 2017Deep & Cross Network for Ad Click Predictionscited by 392
  11. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 326
  12. 2018Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Ratecited by 172
6 more
  1. 2019Improving Generalization in Meta Reinforcement Learning using Learned Objectivescited by 68
  2. 2019Meta-Learning via Learned Losscited by 60
  3. 2018Meta-Learning Update Rules for Unsupervised Representation Learningcited by 37
  4. 2017Related Pins at Pinterest: The Evolution of a Real-World Recommender Systemcited by 24
  5. 2020Online Meta-Critic Learning for Off-Policy Actor-Critic Methodscited by 17
  6. 2017Visual Discovery at Pinterestcited by 11

Built on by

Not cited yet.