No abstract

No abstract

Product quantization (PQ) is a widely used technique for ad-hoc retrieval. Recent studies propose supervised PQ, where the embedding and quantization models can be jointly trained with supervised learning. However, there is a lack of appropriate formulation of the joint training objective; thus, the improvements over previous non-supervised baselines are limited in reality. In this work, we propose the Matching-oriented Product Quantization (MoPQ), where a novel objective Multinoulli Contrastive Loss (MCL) is formulated. With the minimization of MCL, we are able to maximize the matching probability of query and ground-truth key, which contributes to the optimal retrieval accuracy. Given that the exact computation of MCL is intractable due to the demand of vast contrastive samples, we further propose the Differentiable Cross-device Sampling (DCS), which significantly augments the contrastive samples for precise approximation of MCL. We conduct extensive experimental studies on four realworld datasets, whose results verify the effectiveness of MoPQ. The code is available at https://github.com/microsoft/MoPQ. 1. We adopt the Asymmetric Distance Computation (ADC) (Jégou et al., 2011), where only keys need to be quantized.

No abstract

News recommendation calls for deep insights of news articles' underlying semantics. Therefore, pretrained language models (PLMs), like BERT and RoBERTa, may substantially contribute to the recommendation quality. However, it's extremely challenging to have news recommenders trained together with such big models: the learning of news recommenders requires intensive news encoding operations, whose cost is prohibitive if PLMs are used as the news encoder. In this paper, we propose a novel framework, SpeedyFeed, which efficiently trains PLMs-based news recommenders of superior quality. SpeedyFeed is highlighted for its light-weighted encoding pipeline, which gives rise to three major advantages. Firstly, it makes the intermedia results fully reusable for the training workflow, which removes most of the repetitive but redundant encoding operations. Secondly, it improves the data efficiency of the training workflow, where non-informative data can be eliminated from encoding. Thirdly, it further saves the cost by leveraging simplified news encoding and compact news representation.SpeedyFeed leads to more than 100× acceleration of the training process, which enables big models to be trained efficiently and effectively over massive user data. The well-trained PLMs-based model significantly outperforms the state-of-the-art news recommenders in comprehensive offline experiments. It is applied to Microsoft News 1 to empower the training of large-scale production models, which demonstrate highly competitive online performances. SpeedyFeed is also a model-agnostic framework, thus being potentially applicable to a wide spectrum of content-based recommender systems. We've made the source code 2 open to the public so as to facilitate research and applications in related areas.