paper-with-me

홈 › Papers

Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale

2023-11-14 · Wei Wen, Kuang-Hung Liu, Igor Fedorov, Xin Zhang, Hang Yin, Weiwei Chu, Kaveh Hassani, Mengying Sun, Jiang Liu, Xu Wang, Lin Jiang, Yuxin Chen, Buyun Zhang, Xi Liu, Dehua Cheng, Zhengxing Chen, Guang Zhao, Fangqiu Han, Jiyan Yang, Yuchen Hao, Liang Xiong, Wen-Yen Chen

Neural Architecture Search (NAS) has demonstrated its efficacy in computer vision and potential for ranking systems. However, prior work focused on academic problems, which are evaluated at small scale under well-controlled fixed baselines. In industry system, such as ranking system in Meta, it is unclear whether NAS algorithms from the literature can outperform production baselines because of: (1) scale - Meta ranking systems serve billions of users, (2) strong baselines - the baselines are production models optimized by hundreds to thousands of world-class engineers for years since the rise of deep learning, (3) dynamic baselines - engineers may have established new and stronger baselines during NAS search, and (4) efficiency - the search pipeline must yield results quickly in alignment with the productionization life cycle. In this paper, we present Rankitect, a NAS software framework for ranking systems at Meta. Rankitect seeks to build brand new architectures by composing low level building blocks from scratch. Rankitect implements and improves state-of-the-art (SOTA) NAS methods for comprehensive and fair comparison under the same search space, including sampling-based NAS, one-shot NAS, and Differentiable NAS (DNAS). We evaluate Rankitect by comparing to multiple production ranking models at Meta. We find that Rankitect can discover new models from scratch achieving competitive tradeoff between Normalized Entropy loss and FLOPs. When utilizing search space designed by engineers, Rankitect can generate better models than engineers, achieving positive offline evaluation and online A/B test at Meta scale.

📄 PDF Abstract BibTeX arXiv:2311.08430

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture Search

Methods 이 논문이 사용한 방법론

Differentiable NAS 설명 없음

Similar Papers 제목 키워드 기반

Drafting in Collectible Card Games via Reinforcement Learning

2020-11-07 · Ronaldo Vieira, Anderson Rocha Tavares, Luiz Chaimowicz

Collectible card games are played by tens of millions of players worldwide. Their intricate rules and diverse cards make them much harder than traditional card games. To win, players must be proficient in two interdepend…

Card GamesDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1

PAC Battling Bandits in the Plackett-Luce Model

2018-08-12 · Aadirupa Saha, Aditya Gopalan

We introduce the probably approximately correct (PAC) \emph{Battling-Bandit} problem with the Plackett-Luce (PL) subset choice model--an online learning framework where at each trial the learner chooses a subset of $k$ a…

model

The PokeAgent Challenge: Competitive and Long-Context Learning at Scale

2026-03-16 · Seth Karten, Jake Grigsby, Tersoo Upaa, Junik Bae 외 arxiv

We present the PokeAgent Challenge, a large-scale benchmark for decision-making research built on Pokemon's multi-agent battle system and expansive role-playing game (RPG) environment. Partial observability, game-theoret…

Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach

2021-05-17 · Xu Ma, Pengjie Wang, Hui Zhao, Shaoguo Liu 외

In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. Such architecture usually consists of matching, pre-ranking, ranking, and re-ranking stages. In the…

feature selectionRe-Ranking

AutoFAS: Automatic Feature and Architecture Selection for Pre-Ranking System

2022-05-19 · Xiang Li, Xiaojiang Zhou, Yao Xiao, Peihao Huang 외

Industrial search and recommendation systems mostly follow the classic multi-stage information retrieval paradigm: matching, pre-ranking, ranking, and re-ranking stages. To account for system efficiency, simple vector-pr…

Information RetrievalNeural Architecture SearchRecommendation SystemsRe-Ranking+1