Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems
This addresses cost and storage problems for industry-scale recommender systems, but it is incremental as it builds on existing hashing techniques.
The paper tackles the high memory and cost issues of large DNN models in recommender systems by proposing a hybrid hashing method, achieving around 90% model size reduction while maintaining performance comparable to original baselines.
Deep Neural Networks (DNNs) with sparse input features have been widely used in recommender systems in industry. These models have large memory requirements and need a huge amount of training data. The large model size usually entails a cost, in the range of millions of dollars, for storage and communication with the inference services. In this paper, we propose a hybrid hashing method to combine frequency hashing and double hashing techniques for model size reduction, without compromising performance. We evaluate the proposed models on two product surfaces. In both cases, experiment results demonstrated that we can reduce the model size by around 90 % while keeping the performance on par with the original baselines.