As Machine Learning (ML) becomes pervasive in various real world systems, the need for models to be interpretable or explainable has increased. We focus on interpretability, noting that models often need to be constrained in size for them to be considered understandable, e.g., a decision tree of depth 5 is easier to interpret than one of depth 50. This suggests a trade-off between interpretability and accuracy. We propose a technique to minimize this tradeoff. Our strategy is to first learn a powerful, possibly black-box, probabilistic model on the data, which we refer to as the oracle. We use this to adaptively sample the training dataset to present data to our model of interest to learn from. Determining the sampling strategy is formulated as an optimization problem that, independent of the dimensionality of the data, uses only seven variables. We empirically show that this often significantly increases the accuracy of our model. Our technique is model agnostic - in that, both the interpretable model and the oracle might come from any model family. Results using multiple real world datasets, using Linear Probability Models and Decision Trees as interpretable models, and Gradient Boosted Model and Random Forest as oracles are presented. Additionally, we discuss an interesting example of using a sentence-embedding based text classifier as an oracle to improve the accuracy of a term-frequency based bag-of-words linear classifier.

Veriluma Limited (ASX: VRI, Veriluma or Company), one of Australia's leading Artificial Intelligence companies providing prescriptive analytics software solutions, is[…]

In this work we examine the problematic associated to the development of machine learning models to achieve robust generalization capabilities on common-task multiple-database scenarios. Referred as the ''database variability problem'', we focus on a specific medical domain (sleep staging in Sleep Medicine) to show the non-triviality of translating the estimated model's local generalization capabilities to independent external databases. We analyze some of the scalability problems when multiple-database data are used as input to train a single learning model. Then, we introduce a novel approach based on an ensemble of local models, and we show its advantages in terms of inter-database generalization performance and data scalability. Further on, we analyze different model configurations and data pre-processing techniques to evaluate their effects over the overall generalization performance. For this purpose we carry out experimentation involving several sleep databases evaluating different machine learning models based on Convolutional Neural Networks

Jin Hyun Kim (Humboldt University of Berlin, Germany, Music) - Our self and the world enhanced by music's mediating relations

Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step frameworks are difficult to manipulate and usually lead to suboptimal performance, mainly because the graph embedding is not goal-directed, i.e., designed for the specific clustering task. In this paper, we propose a goal-directed deep learning approach, Deep Attentional Embedded Graph Clustering (DAEGC for short). Our method focuses on attributed graphs to sufficiently explore the two sides of information in graphs. By employing an attention network to capture the importance of the neighboring nodes to a target node, our DAEGC algorithm encodes the topological structure and node content in a graph to a compact representation, on which an inner product decoder is trained to reconstruct the graph structure. Furthermore, soft labels from the graph embedding itself are generated to supervise a self-training graph clustering process, which iteratively refines the clustering results. The self-training process is jointly learned and optimized with the graph embedding in a unified framework, to mutually benefit both components. Experimental results compared with state-of-the-art algorithms demonstrate the superiority of our method.

Human domain experts solve difficult planning problems by drawing on years of experience. In many cases, computing a solution to such problems is computationally intractable or requires encoding heuristics from human domain experts. As codifying this knowledge leaves much to be desired, we aim to infer their strategies through observation. The challenge lies in that humans exhibit heterogeneity in their latent decision-making criteria. To overcome this, we propose a personalized apprenticeship learning framework that automatically infers a representation of all human task demonstrators by extracting a human-specific embedding. Our framework is built on a propositional architecture that allows for distilling an interpretable representation of each human demonstrator's decision-making.

This paper presents the experiments accomplished as a part of our participation in the MEDIQA challenge, an (Abacha et al., 2019) shared task. We participated in all the three tasks defined in this particular shared task. The tasks are viz. i. Natural Language Inference (NLI) ii. Recognizing Question Entailment(RQE) and their application in medical Question Answering (QA). We submitted runs using multiple deep learning based systems (runs) for each of these three tasks. We submitted five system results in each of the NLI and RQE tasks, and four system results for the QA task. The systems yield encouraging results in all three tasks. The highest performance obtained in NLI, RQE and QA tasks are 81.8%, 53.2%, and 71.7%, respectively.

This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of learning temporal relationships and translation invariant representations, is used for robust acoustic modelling. Further, i-vectors were used as an input to the neural network to perform instantaneous speaker and environment adaptation, providing 8\% relative improvement in word error rate on the NIST Hub5 2000 evaluation test set. By enhancing the first-pass i-vector based adaptation with a second-pass adaptation using speaker and environment dependent transformations within the network, a further relative improvement of 5\% in word error rate was achieved. We have reevaluated the features used to estimate i-vectors and their normalization to achieve the best performance in a modern large scale automatic speech recognition system.

In personalised decision making, evidence is required to determine suitable actions for individuals. Such evidence can be obtained by identifying treatment effect heterogeneity in different subgroups of the population. In this paper, we design a new type of pattern, treatment effect pattern to represent and discover treatment effect heterogeneity from data for determining whether a treatment will work for an individual or not. Our purpose is to use the computational power to find the most specific and relevant conditions for individuals with respect to a treatment or an action to assist with personalised decision making. Most existing work on identifying treatment effect heterogeneity takes a top-down or partitioning based approach to search for subgroups with heterogeneous treatment effects. We propose a bottom-up generalisation algorithm to obtain the most specific patterns that fit individual circumstances the best for personalised decision making. For the generalisation, we follow a consistency driven strategy to maintain inner-group homogeneity and inter-group heterogeneity of treatment effects. We also employ graphical causal modelling technique to identify adjustment variables for reliable treatment effect pattern discovery. Our method can find the treatment effect patterns reliably as validated by the experiments. The method is faster than the two existing machine learning methods for heterogeneous treatment effect identification and it produces subgroups with higher inner-group treatment effect homogeneity.

The deep layers of modern neural networks extract a rather rich set of features as an input propagates through the network. This paper sets out to harvest these rich intermediate representations for quantization with minimal accuracy loss while significantly reducing the memory footprint and compute intensity of the DNN. This paper utilizes knowledge distillation through teacher-student paradigm (Hinton et al., 2015) in a novel setting that exploits the feature extraction capability of DNNs for higher-accuracy quantization. As such, our algorithm logically divides a pretrained full-precision DNN to multiple sections, each of which exposes intermediate features to train a team of students independently in the quantized domain. This divide and conquer strategy, in fact, makes the training of each student section possible in isolation while all these independently trained sections are later stitched together to form the equivalent fully quantized network. Experiments on various DNNs (LeNet, ResNet-20, SVHN and VGG-11) show that, on average, this approach - called DCQ (Divide and Conquer Quantization) - achieves on average 9.7% accuracy improvement to a state-of-the-art quantized training technique, DoReFa (Zhou et al., 2016) for binary and ternary networks.