Distilled Neural Networks for Efficient Learning to Rank
Authors:
- 18 February 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Abstract
Recent studies in Learning to Rank have shown the possibility to effectively distill a neural network from an ensemble of regression trees. This result leads neural networks to become a natural competitor of tree-based ensembles on the ranking task. Nevertheless, ensembles of regression trees outperform neural models both in terms of efficiency and effectiveness, particularly when scoring on CPU. In this paper, we propose an approach for speeding up neural scoring time by applying a combination of Distillation, Pruning and Fast Matrix multiplication. We employ knowledge distillation to learn shallow neural networks from an ensemble of regression trees. Then, we exploit an efficiency-oriented pruning technique that performs a sparsification of the most computationally-intensive layers of the neural network that is then scored with optimized sparse matrix multiplication. Moreover, by studying both dense and sparse high performance matrix multiplication, we develop a scoring time prediction model which helps in devising neural network architectures that match the desired efficiency requirements. Comprehensive experiments on two public learning-to-rank datasets show that neural networks produced with our novel approach are competitive at any point of the effectiveness-efficiency trade-off when compared with tree-based ensembles, providing up to 4x scoring time speed-up without affecting the ranking quality.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- BLIS: A Framework for Rapidly Instantiating BLAS FunctionalityACM Transactions on Mathematical Software, 2015
- Intel Math Kernel Library2014
- Scalability Challenges in Web Search Engines2011
- Fast Nonnegative Matrix Factorization: An Active-Set-Like Method and ComparisonsSIAM Journal on Scientific Computing, 2011
- Anatomy of high-performance matrix multiplicationACM Transactions on Mathematical Software, 2008
- Constructive Approximation of Discontinuous Functions by Neural NetworksNeural Processing Letters, 2008
- Cumulated gain-based evaluation of IR techniquesACM Transactions on Information Systems, 2002
- All-Pairs Shortest Paths Computation in the BSP Model2001
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Basic Linear Algebra Subprograms for Fortran UsageACM Transactions on Mathematical Software, 1979