NSL: Hybrid Interpretable Learning From Noisy Raw Data

Inductive Logic Programming (ILP) systems learn generalised, interpretable rules in a data-efficient manner utilising existing background knowledge. However, current ILP systems require training examples to be specified in a structured logical format. Neural networks learn from unstructured data, although their learned models may be difficult to interpret and are vulnerable to data perturbations at run-time. This paper introduces a hybrid neural-symbolic learning framework, called NSL, that learns interpretable rules from labelled unstructured data. NSL combines pre-trained neural networks for feature extraction with FastLAS, a state-of-the-art ILP system for rule learning under the answer set semantics. Features extracted by the neural components define the structured context of labelled examples and the confidence of the neural predictions determines the level of noise of the examples. Using the scoring function of FastLAS, NSL searches for short, interpretable rules that generalise over such noisy examples. We evaluate our framework on propositional and first-order classification tasks using the MNIST dataset as raw data. Specifically, we demonstrate that NSL is able to learn robust rules from perturbed MNIST data and achieve comparable or superior accuracy when compared to neural network and random forest baselines whilst being more general and interpretable.

[1]  Wannes Meert,et al.  The Most Probable Explanation for Probabilistic Logic Programs with Annotated Disjunctions , 2014, ILP.

[2]  Luc De Raedt,et al.  DeepProbLog: Neural Probabilistic Logic Programming , 2018, BNAIC/BENELEARN.

[3]  Abhishek Verma,et al.  Deep CNN-LSTM with combined kernels from multiple branches for IMDb review sentiment analysis , 2017, 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON).

[4]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[5]  Jorge Lobo,et al.  FastLAS: Scalable Inductive Logic Programming Incorporating Domain-Specific Optimisation Criteria , 2020, AAAI.

[6]  Christian Eitzinger,et al.  Triangular Norms , 2001, Künstliche Intell..

[7]  Stephen Muggleton,et al.  Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP , 2018, Machine Learning.

[8]  Murat Sensoy,et al.  Evidential Deep Learning to Quantify Classification Uncertainty , 2018, NeurIPS.

[9]  Zhiyuan Liu,et al.  A C-LSTM Neural Network for Text Classification , 2015, ArXiv.

[10]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[11]  Lalana Kagal,et al.  Explaining Explanations: An Overview of Interpretability of Machine Learning , 2018, 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA).

[12]  Brandon M. Greenwell,et al.  Interpretable Machine Learning , 2019, Hands-On Machine Learning with R.

[13]  Richard Evans,et al.  Learning Explanatory Rules from Noisy Data , 2017, J. Artif. Intell. Res..

[14]  Ratula Ray,et al.  Comparative Study of the Ensemble Learning Methods for Classification of Animals in the Zoo , 2019, Smart Intelligent Computing and Applications.

[15]  Andrew Cropper,et al.  Turning 30: New Ideas in Inductive Logic Programming , 2020, ArXiv.

[16]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[17]  Artur S. d'Avila Garcez,et al.  Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge , 2016, NeSy@HLAI.

[18]  Vítor Santos Costa,et al.  Inductive Logic Programming , 2013, Lecture Notes in Computer Science.

[19]  D. Gabbay,et al.  Proof Theory for Fuzzy Logics , 2008 .

[20]  Jure Leskovec,et al.  Interpretable Decision Sets: A Joint Framework for Description and Prediction , 2016, KDD.

[21]  Stephen Muggleton,et al.  Bias reformulation for one-shot function induction , 2014, ECAI.

[22]  Murat Sensoy,et al.  Uncertainty-Aware Deep Classifiers Using Generative Models , 2020, AAAI.

[23]  Samy S. Abu-Naser,et al.  Artificial Neural Network for Predicting Animals Category , 2019 .

[24]  Jorge Lobo,et al.  Risk-based access control systems built on fuzzy inferences , 2010, ASIACCS '10.

[25]  Krysia Broda,et al.  Inductive Learning of Answer Set Programs from Noisy Examples , 2018, ArXiv.

[26]  Krysia Broda,et al.  Inductive Learning of Answer Set Programs , 2014, JELIA.

[27]  Luc De Raedt,et al.  ProbLog: A Probabilistic Prolog and its Application in Link Discovery , 2007, IJCAI.

[28]  Krysia Broda,et al.  Logic-Based Learning of Answer Set Programs , 2019, Reasoning Web.