Session

Session 10: Techniques, and more Techniques

Moderator: Paul Whatmough



Abstract:

Chat is not available.

Thu 8 April 11:10 - 11:30 PDT
SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection

Yue Zhao · Xiyang Hu · Cheng Cheng · Cong Wang · Changlin Wan · Wen Wang · Jianing Yang · Haoping Bai · Zheng Li · Cao Xiao · Yunlong Wang · Zhi Qiao · Jimeng Sun · Leman Akoglu

Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples with numerous high-stake applications including fraud detection and intrusion detection. Due to the lack of ground truth labels, practitioners often have to build a large number of unsupervised, heterogeneous models (i.e., different algorithms with varying hyperparameters) for further combination and analysis, rather than relying on a single model. How to accelerate the training and scoring on new-coming samples by outlyingness (referred as prediction throughout the paper) with a large number of unsupervised, heterogeneous OD models? In this study, we propose a modular acceleration system, called SUOD, to address it. The proposed system focuses on three complementary acceleration aspects (data reduction for high-dimensional data, approximation for costly models, and taskload imbalance optimization for distributed environment), while maintaining performance accuracy. Extensive experiments on more than 20 benchmark datasets demonstrate SUOD's effectiveness in heterogeneous OD acceleration, along with a real-world deployment case on fraudulent claim analysis at IQVIA, a leading healthcare firm. We open-source SUOD for reproducibility and accessibility.

[ Paper PDF
[ ]
Thu 8 April 11:30 - 11:50 PDT
Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy

Lucas Liebenwein · Cenk Baykal · Brandon Carter · David Gifford · Daniela Rus

Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks. Starting from a pre-trained network, the process is as follows: remove redundant parameters, retrain, and repeat while maintaining the same test accuracy. The result is a model that is a fraction of the size of the original with comparable predictive performance (test accuracy). Here, we reassess and evaluate whether the use of test accuracy alone in the terminating condition is sufficient to ensure that the resulting model performs well across a wide spectrum of "harder" metrics such as generalization to out-of-distribution data and resilience to noise. Across evaluations on varying architectures and data sets, we find that pruned networks effectively approximate the unpruned model, however, the prune ratio at which pruned networks achieve commensurate performance varies significantly across tasks. These results call into question the extent of \emph{genuine} overparameterization in deep learning and raise concerns about the practicability of deploying pruned networks, specifically in the context of safety-critical systems, unless they are widely evaluated beyond test accuracy to reliably predict their performance. Our code is available at https://github.com/lucaslie/torchprune.

[ Paper PDF
[ ]
Thu 8 April 11:50 - 12:10 PDT
Equality Saturation for Tensor Graph Superoptimization

Yichen Yang · Phitchaya Phothilimthana · Yisu Wang · Max Willsey · Sudip Roy · Jacques Pienaar

One of the major optimizations employed in deep learning frameworks is graph rewriting. Production frameworks rely on heuristics to decide if rewrite rules should be applied and in which order. Prior research has shown that one can discover more optimal tensor computation graphs if we search for a better sequence of substitutions instead of relying on heuristics. However, we observe that existing approaches for tensor graph superoptimization both in production and research frameworks apply substitutions in a sequential manner. Such sequential search methods are sensitive to the order in which the substitutions are applied and often only explore a small fragment of the exponential space of equivalent graphs. This paper presents a novel technique for tensor graph superoptimization that employs equality saturation to apply all possible substitutions at once. We show that our approach can find optimized graphs with up to 16% speedup over state-of-the-art, while spending on average 48x less time optimizing.

[ Paper PDF
[ ]
Thu 8 April 12:10 - 12:30 PDT
Doping: A technique for Extreme Compression of LSTM Models using Sparse Structured Additive Matrices

Urmish Thakker · Paul Whatmough · ZHIGANG LIU · Matthew Mattina · Jesse Beu

Structured matrices, such as those derived from Kronecker products (KP), are effective at compressing neural networks, but can lead to unacceptable accuracy loss when applied to large models. In this paper, we propose the notion of doping - addition of an extremely sparse matrix to a structured matrix. Doping facilitates additional degrees of freedom for a small number of parameters, allowing them to independently diverge from the fixed structure. To train LSTMs with doped structured matrices, we introduce the additional parameter matrix while slowly annealing its sparsity level. However, we find that performance degrades as we slowly sparsify the doping matrix, due to co-matrix adaptation (CMA) between the structured and the sparse matrices. We address this over dependence on the sparse matrix using a co-matrix dropout regularization (CMR) scheme. We provide empirical evidence to show that doping, CMA and CMR are concepts generally applicable to multiple structured matrices (Kronecker Product, LMF, Hybrid Matrix Decomposition). Additionally, results with doped kronecker product matrices demonstrate state-of-the-art accuracy at large compression factors (10 − 25x) across 4 natural language processing applications with minor loss in accuracy. Doped KP compression technique outperforms previous state-of-the art compression results by achieving 1.3−2.4x higher compression factor at a similar accuracy, while also beating strong alternatives like pruning and low-rank methods by a large margin (8% or more). Additionally, we show that doped KP can be deployed on commodity hardware using the current software stack and achieve 2.5 − 5.5x inference run-time speed-up over baseline.

[ Paper PDF
[ ]