Efficient Decompositional Rule Extraction for Deep Neural Networks

• URL: http://arxiv.org/abs/2111.12628v1
• Date: Wed, 24 Nov 2021 16:54:10 GMT
• Title: Efficient Decompositional Rule Extraction for Deep Neural Networks
• Authors: Mateo Espinosa Zarlenga, Zohreh Shams, Mateja Jamnik
• Abstract summary: ECLAIRE is a novel-time rule extraction algorithm capable of scaling to both large DNN architectures and large training datasets. We show that ECLAIRE consistently extracts more accurate and comprehensible rule sets than the current state-of-the-art methods.
• Score: 5.69361786082969
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, there has been significant work on increasing both interpretability and debuggability of a Deep Neural Network (DNN) by extracting a rule-based model that approximates its decision boundary. Nevertheless, current DNN rule extraction methods that consider a DNN's latent space when extracting rules, known as decompositional algorithms, are either restricted to single-layer DNNs or intractable as the size of the DNN or data grows. In this paper, we address these limitations by introducing ECLAIRE, a novel polynomial-time rule extraction algorithm capable of scaling to both large DNN architectures and large training datasets. We evaluate ECLAIRE on a wide variety of tasks, ranging from breast cancer prognosis to particle detection, and show that it consistently extracts more accurate and comprehensible rule sets than the current state-of-the-art methods while using orders of magnitude less computational resources. We make all of our methods available, including a rule set visualisation interface, through the open-source REMIX library (https://github.com/mateoespinosa/remix).

Related papers

• Taming Reachability Analysis of DNN-Controlled Systems via Abstraction-Based Training [14.787056022080625]
  This paper presents a novel abstraction-based approach to bypass the crux of over-approximating DNNs in reachability analysis. We extend conventional DNNs by inserting an additional abstraction layer, which abstracts a real number to an interval for training. We devise the first black-box reachability analysis approach for DNN-controlled systems, where trained DNNs are only queried as black-box oracles for the actions on abstract states.
  arXiv  Detail & Related papers  (2022-11-21T00:11:50Z)
• Masked Bayesian Neural Networks : Computation and Optimality [1.3649494534428745]
  We propose a novel sparse Bayesian neural network (BNN) which searches a good deep neural network with an appropriate complexity. We employ the masking variables at each node which can turn off some nodes according to the posterior distribution to yield a nodewise sparse DNN. By analyzing several benchmark datasets, we illustrate that the proposed BNN performs well compared to other existing methods.
  arXiv  Detail & Related papers  (2022-06-02T02:59:55Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• EIGNN: Efficient Infinite-Depth Graph Neural Networks [51.97361378423152]
  Graph neural networks (GNNs) are widely used for modelling graph-structured data in numerous applications. Motivated by this limitation, we propose a GNN model with infinite depth, which we call Efficient Infinite-Depth Graph Neural Networks (EIGNN) We show that EIGNN has a better ability to capture long-range dependencies than recent baselines, and consistently achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-02-22T08:16:58Z)
• Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers [67.688697838109]
  This paper presents a novel method to train quantized RNNLMs from scratch using alternating direction methods of multipliers (ADMM) Experiments on two tasks suggest the proposed ADMM quantization achieved a model size compression factor of up to 31 times over the full precision baseline RNNLMs.
  arXiv  Detail & Related papers  (2021-11-29T09:30:06Z)
• Pruning and Slicing Neural Networks using Formal Verification [0.2538209532048866]
  Deep neural networks (DNNs) play an increasingly important role in various computer systems. In order to create these networks, engineers typically specify a desired topology, and then use an automated training algorithm to select the network's weights. Here, we propose to address this challenge by harnessing recent advances in DNN verification.
  arXiv  Detail & Related papers  (2021-05-28T07:53:50Z)
• Consistent Sparse Deep Learning: Theory and Computation [11.24471623055182]
  We propose a frequentist-like method for learning sparse deep learning networks (DNNs) The proposed method can perform very well for large-scale network compression and high-dimensional nonlinear variable selection.
  arXiv  Detail & Related papers  (2021-02-25T23:31:24Z)
• Online Limited Memory Neural-Linear Bandits with Likelihood Matching [53.18698496031658]
  We study neural-linear bandits for solving problems where both exploration and representation learning play an important role. We propose a likelihood matching algorithm that is resilient to catastrophic forgetting and is completely online.
  arXiv  Detail & Related papers  (2021-02-07T14:19:07Z)
• Chance-Constrained Control with Lexicographic Deep Reinforcement Learning [77.34726150561087]
  This paper proposes a lexicographic Deep Reinforcement Learning (DeepRL)-based approach to chance-constrained Markov Decision Processes. A lexicographic version of the well-known DeepRL algorithm DQN is also proposed and validated via simulations.
  arXiv  Detail & Related papers  (2020-10-19T13:09:14Z)
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks [80.15411508088522]
  Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency. We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
  arXiv  Detail & Related papers  (2020-07-02T15:38:44Z)
• Fractional Deep Neural Network via Constrained Optimization [0.0]
  This paper introduces a novel algorithmic framework for a deep neural network (DNN) Fractional-DNN can be viewed as a time-discretization of a fractional in time nonlinear ordinary differential equation (ODE)
  arXiv  Detail & Related papers  (2020-04-01T21:58:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.