Multiscale Quantization for Fast Similarity Search

By Xiang Wu, Ruiqi Guo, Ananda Theertha Suresh, Sanjiv Kumar, Daniel Niels Holtmann-Rice, David Simcha, Felix X. Yu. 2017

80 citations recorded by the source corpus.

Subfields: Information Retrieval & Search, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

1. Sanjiv Kumar
2. Ruiqi Guo
3. David Simcha
4. Felix X. Yu
5. Liu Yang
6. Rafael G. L. D'Oliveira
7. Dawn Song
8. Ramesh Raskar

In Efficiency & Compression

1. Medhi Bennis
2. Jakub Konecný
3. Oluwasanmi Koyejo
4. Martin Jaggi
5. Ananda Theertha Suresh
6. Qiang Yang
7. Sebastian U. Stich
8. Mehryar Mohri

Citations in the corpus

• Advances and Open Problems in Federated Learning (2019, background): “Similarly, recent works show that learning a compression scheme in a data-dependent fashion can lead to significantly better compression ratio for the case of data compression [412] as well as gradient compression.”
• Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning (2019, methodology): “Inspired by vector quantization techniques (Chen et al., 2010; Ge et al., 2013; Jegou et al., 2011; Wu et al., 2017), HSQ adopts a paradigm that is fundamentally different from existing gradient compression algorithms (Bernstein et al., 2018; Wen et al., 2017).”
• Sampling-bias-corrected neural modeling for large corpus item recommendations (2019, background): “Specifcally, compact representations of high dimensional embeddings are built through quantization [20] and end-to-end learning of coarse and product quantizers [36].”
• Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Document Matching (2020, methodology): “To solve this problem, we learn query independent document representations and index them offline to serve with efficient similarity search libraries [14, 31].”
• Accelerating Large-Scale Inference with Anisotropic Vector Quantization (2019, methodology): “…we learn embedding functions to map items to be retrieved in a common vector space, where the items can be words, images, users, audio, products, web pages, graph nodes, or anything of interest (Cremonesi et al., 2010; Weston et al., 2010; Guo et al., 2016a; Gillick et al., 2019; Wu et al., 2017).”
• Factorized Deep Retrieval and Distributed TensorFlow Serving (2018, background): “Specifically, compact representation of high dimensional embeddings are built through quantization [5] and end-to-end learning of coarse and product quantizers [12].”