Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RD5Z466Hrecord.jsonopen to challenge →
read the original abstract
One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an inner-product model, and then use some approximate nearest neighbor (ANN) search algorithm to find top candidates. In this paper, we present Deep Retrieval (DR), to learn a retrievable structure directly with user-item interaction data (e.g. clicks) without resorting to the Euclidean space assumption in ANN algorithms. DR's structure encodes all candidate items into a discrete latent space. Those latent codes for the candidates are model parameters and learnt together with other neural network parameters to maximize the same objective function. With the model learnt, a beam search over the structure is performed to retrieve the top candidates for reranking. Empirically, we first demonstrate that DR, with sub-linear computational complexity, can achieve almost the same accuracy as the brute-force baseline on two public datasets. Moreover, we show that, in a live production recommendation system, a deployed DR approach significantly outperforms a well-tuned ANN baseline in terms of engagement metrics. To the best of our knowledge, DR is among the first non-ANN algorithms successfully deployed at the scale of hundreds of millions of items for industrial recommendation systems.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling
The framework replaces Video IDs with depth-truncated Semantic IDs and introduces a Global-Aware Compression Transformer to model ultra-long user sequences at billion-user scale with reduced memory and compute.
-
Efficient Retrieval Scaling with Hierarchical Indexing for Large Scale Recommendation
A jointly learned hierarchical index with cross-attention and residual quantization scales exact retrieval in foundational recommendation models, deployed at Meta with additional performance from test-time training on...
-
From Extraction to Navigation: Progressive Retrieval with Indirectly Infinite Depth
IID-Nav enables progressive retrieval in large-scale recommenders by treating it as iterative goal-driven graph traversal with recursive state evolution supporting unlimited depth without rising inference cost.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.