license: mit
datasets:
- natural_questions
pipeline_tag: question-answering
AdANNS: A Framework for Adaptive Semantic Search 馃拑
Aniket Rege*, Aditya Kusupati*, Sharan Ranjit S, Alan Fan, Qinqqing Cao, Sham Kakade, Prateek Jain, Ali Farhadi
GitHub: https://github.com/RAIVNLab/AdANNS
Arxiv: https://arxiv.org/abs/2305.19435
Adaptive representations can be utilized effectively in the decoupled components of clustering and
searching for a better accuracy-compute trade-off (AdANNS-IVF).
We provide four BERT-Base models finetuned on Natural Questions with Matryoshka Representation Learning (MRL).
A vanilla pretrained BERT-Base has a 768-d representation (information bottleneck). As we train with MRL, we enforce the network to learn representations at
multiple granularities nested within a 768-d embedding. The granularities at which we finetune BERT-Base with Matroyshka Loss are specified in the folder name,
e.g. for dpr-nq-d768_384_192_96_48, we have d=[48, 96, 192, 384, 768].
You can easily load an mrl-nq model as follows:
from transformers import BertModel
import torch
model = BertModel.from_pretrained('dpr-nq-d768_384_192_96_48')
Citation
If you find this project useful in your research, please consider citing:
@inproceedings{rege2023adanns,
title={AdANNS: A Framework for Adaptive Semantic Search},
author={Aniket Rege and Aditya Kusupati and Sharan Ranjit S and Alan Fan and Qingqing Cao and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2023},
booktitle = {Advances in Neural Information Processing Systems},
month = {December},
year = {2023},
}