Clustering is Efficient for Approximate Maximum Inner Product Search

By Alex Auvolat, Sarath Chandar, Pascal Vincent, Hugo Larochelle, Yoshua Bengio. 2015

47 citations recorded by the source corpus.

Subfields: Information Retrieval & Search

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. Ruiqi Guo
2. Sanjiv Kumar
3. Rami Al-Rfou
4. A. P. Sarath Chandar
5. Pascal Vincent
6. G. Tesauro
7. Yoshua Bengio
8. Stephen O. Mussmann

Citations in the corpus

• Efficient Natural Language Response Suggestion for Smart Reply (2017, methodology): “The curve is produced by varying the number of approximate neighbors retrieved by our hierarchical quantization method and by Asymmetric LSH [22], and varying the number of leaves searched by the clustering algorithm of [3].”
• Learning and Inference via Maximum Inner Product Search (2016, methodology): “For this experiment, we also include results from using the hierarchical spherical k-means algorithm (HSKM) (Auvolat et al., 2015) as the MIPS method.”
• Hierarchical Memory Networks (2016, methodology): “Instead, [11] appends additional dimensions to both query and data vectors to convert MIPS to MCSS.”
• A^3: Accelerating Attention Mechanisms in Neural Networks with Approximation (2020, methodology): “For example, some approaches [56], [57], [58] utilize a variant of locality sensitive hashing, a tree-structure, or a”