Abstract
Feature hashing is widely used to process large scale sparse features for learning of predictive models. Collisions inherently happen in the hashing process and hurt the model performance. In this paper, we develop a new feature hashing scheme called Cuckoo Feature Hashing (CCFH), which treats feature hashing as a problem of dynamic weight sharing during model training. By leveraging a set of indicators to dynamically decide the weight of each feature based on alternative hash locations, CCFH effectively prevents the collisions between important features to the model, i.e. predictive features, and thus avoid model performance degradation. Experimental results on prediction tasks with hundred-millions of features demonstrate that CCFH can achieve the same level of performance by using only 15%-25% parameters compared with conventional feature hashing.