October 17, 2019

3093 words 15 mins read

Paper Group ANR 766

Substitute Teacher Networks: Learning with Almost No Supervision. Explicating feature contribution using Random Forest proximity distances. State Aggregation Learning from Markov Transition Data. RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records. Automated Reasoning in Normative D …

Substitute Teacher Networks: Learning with Almost No Supervision


Title	Substitute Teacher Networks: Learning with Almost No Supervision
Authors	Samuel Albanie, James Thewlis, Joao F. Henriques
Abstract	Learning through experience is time-consuming, inefficient and often bad for your cortisol levels. To address this problem, a number of recently proposed teacher-student methods have demonstrated the benefits of private tuition, in which a single model learns from an ensemble of more experienced tutors. Unfortunately, the cost of such supervision restricts good representations to a privileged minority. Unsupervised learning can be used to lower tuition fees, but runs the risk of producing networks that require extracurriculum learning to strengthen their CVs and create their own LinkedIn profiles. Inspired by the logo on a promotional stress ball at a local recruitment fair, we make the following three contributions. First, we propose a novel almost no supervision training algorithm that is effective, yet highly scalable in the number of student networks being supervised, ensuring that education remains affordable. Second, we demonstrate our approach on a typical use case: learning to bake, developing a method that tastily surpasses the current state of the art. Finally, we provide a rigorous quantitive analysis of our method, proving that we have access to a calculator. Our work calls into question the long-held dogma that life is the best teacher.
Tasks
Published	2018-04-01
URL	http://arxiv.org/abs/1803.11560v1
PDF	http://arxiv.org/pdf/1803.11560v1.pdf
PWC	https://paperswithcode.com/paper/substitute-teacher-networks-learning-with
Repo
Framework

Explicating feature contribution using Random Forest proximity distances


Title	Explicating feature contribution using Random Forest proximity distances
Authors	Leanne S. Whitmore, Anthe George, Corey M. Hudson
Abstract	In Random Forests, proximity distances are a metric representation of data into decision space. By observing how changes in input map to the movement of instances in this space we are able to determine the independent contribution of each feature to the decision-making process. For binary feature vectors, this process is fully specified. As these changes in input move particular instances nearer to the in-group or out-group, the independent contribution of each feature can be uncovered. Using this technique, we are able to calculate the contribution of each feature in determining how black-box decisions were made. This allows explication of the decision-making process, audit of the classifier, and post-hoc analysis of errors in classification.
Tasks	Decision Making
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06572v1
PDF	http://arxiv.org/pdf/1807.06572v1.pdf
PWC	https://paperswithcode.com/paper/explicating-feature-contribution-using-random
Repo
Framework

State Aggregation Learning from Markov Transition Data


Title	State Aggregation Learning from Markov Transition Data
Authors	Yaqi Duan, Zheng Tracy Ke, Mengdi Wang
Abstract	State aggregation is a popular model reduction method rooted in optimal control. It reduces the complexity of engineering systems by mapping the system’s states into a small number of meta-states. The choice of aggregation map often depends on the data analysts’ knowledge and is largely ad hoc. In this paper, we propose a tractable algorithm that estimates the probabilistic aggregation map from the system’s trajectory. We adopt a soft-aggregation model, where each meta-state has a signature raw state, called an anchor state. This model includes several common state aggregation models as special cases. Our proposed method is a simple two-step algorithm: The first step is spectral decomposition of empirical transition matrix, and the second step conducts a linear transformation of singular vectors to find their approximate convex hull. It outputs the aggregation distributions and disaggregation distributions for each meta-state in explicit forms, which are not obtainable by classical spectral methods. On the theoretical side, we prove sharp error bounds for estimating the aggregation and disaggregation distributions and for identifying anchor states. The analysis relies on a new entry-wise deviation bound for singular vectors of the empirical transition matrix of a Markov process, which is of independent interest and cannot be deduced from existing literature. The application of our method to Manhattan traffic data successfully generates a data-driven state aggregation map with nice interpretations.
Tasks
Published	2018-11-06
URL	https://arxiv.org/abs/1811.02619v3
PDF	https://arxiv.org/pdf/1811.02619v3.pdf
PWC	https://paperswithcode.com/paper/state-aggregation-learning-from-markov
Repo
Framework

RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records


Title	RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records
Authors	Bum Chul Kwon, Min-Je Choi, Joanne Taery Kim, Edward Choi, Young Bin Kim, Soonwook Kwon, Jimeng Sun, Jaegul Choo
Abstract	We have recently seen many successful applications of recurrent neural networks (RNNs) on electronic medical records (EMRs), which contain histories of patients’ diagnoses, medications, and other various events, in order to predict the current and future states of patients. Despite the strong performance of RNNs, it is often challenging for users to understand why the model makes a particular prediction. Such black-box nature of RNNs can impede its wide adoption in clinical practice. Furthermore, we have no established methods to interactively leverage users’ domain expertise and prior knowledge as inputs for steering the model. Therefore, our design study aims to provide a visual analytics solution to increase interpretability and interactivity of RNNs via a joint effort of medical experts, artificial intelligence scientists, and visual analytics researchers. Following the iterative design process between the experts, we design, implement, and evaluate a visual analytics tool called RetainVis, which couples a newly improved, interpretable and interactive RNN-based model called RetainEX and visualizations for users’ exploration of EMR data in the context of prediction tasks. Our study shows the effective use of RetainVis for gaining insights into how individual medical codes contribute to making risk predictions, using EMRs of patients with heart failure and cataract symptoms. Our study also demonstrates how we made substantial changes to the state-of-the-art RNN model called RETAIN in order to make use of temporal information and increase interactivity. This study will provide a useful guideline for researchers that aim to design an interpretable and interactive visual analytics tool for RNNs.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1805.10724v3
PDF	http://arxiv.org/pdf/1805.10724v3.pdf
PWC	https://paperswithcode.com/paper/retainvis-visual-analytics-with-interpretable
Repo
Framework

Automated Reasoning in Normative Detachment Structures with Ideal Conditions


Title	Automated Reasoning in Normative Detachment Structures with Ideal Conditions
Authors	Tomer Libal, Matteo Pascucci
Abstract	Systems of deontic logic suffer either from being too expressive and therefore hard to mechanize, or from being too simple to capture relevant aspects of normative reasoning. In this article we look for a suitable way in between: the automation of a simple logic of normative ideality and sub-ideality that is not affected by many deontic paradoxes and that is expressive enough to capture contrary-to-duty reason- ing. We show that this logic is very useful to reason on normative scenarios from which one can extract a certain kind of argumentative structure, called a Normative Detachment Structure with Ideal Conditions. The theoretical analysis of the logic is accompanied by examples of automated reasoning on a concrete legal text.
Tasks
Published	2018-10-23
URL	http://arxiv.org/abs/1810.09993v1
PDF	http://arxiv.org/pdf/1810.09993v1.pdf
PWC	https://paperswithcode.com/paper/automated-reasoning-in-normative-detachment
Repo
Framework

Set Cross Entropy: Likelihood-based Permutation Invariant Loss Function for Probability Distributions


Title	Set Cross Entropy: Likelihood-based Permutation Invariant Loss Function for Probability Distributions
Authors	Masataro Asai
Abstract	We propose a permutation-invariant loss function designed for the neural networks reconstructing a set of elements without considering the order within its vector representation. Unlike popular approaches for encoding and decoding a set, our work does not rely on a carefully engineered network topology nor by any additional sequential algorithm. The proposed method, Set Cross Entropy, has a natural information-theoretic interpretation and is related to the metrics defined for sets. We evaluate the proposed approach in two object reconstruction tasks and a rule learning task.
Tasks	Object Reconstruction
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01217v2
PDF	http://arxiv.org/pdf/1812.01217v2.pdf
PWC	https://paperswithcode.com/paper/set-cross-entropy-likelihood-based
Repo
Framework

Reinforcement Learning for Uplift Modeling


Title	Reinforcement Learning for Uplift Modeling
Authors	Chenchen Li, Xiang Yan, Xiaotie Deng, Yuan Qi, Wei Chu, Le Song, Junlong Qiao, Jianshan He, Junwu Xiong
Abstract	Uplift modeling aims to directly model the incremental impact of a treatment on an individual response. In this work, we address the problem from a new angle and reformulate it as a Markov Decision Process (MDP). We conducted extensive experiments on both a synthetic dataset and real-world scenarios, and showed that our method can achieve significant improvement over previous methods.
Tasks
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10158v2
PDF	http://arxiv.org/pdf/1811.10158v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-for-uplift-modeling
Repo
Framework

SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation


Title	SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation
Authors	Ye Zhang, Nan Ding, Radu Soricut
Abstract	Supervised training of abstractive language generation models results in learning conditional probabilities over language sequences based on the supervised training signal. When the training signal contains a variety of writing styles, such models may end up learning an ‘average’ style that is directly influenced by the training data make-up and cannot be controlled by the needs of an application. We describe a family of model architectures capable of capturing both generic language characteristics via shared model parameters, as well as particular style characteristics via private model parameters. Such models are able to generate language according to a specific learned style, while still taking advantage of their power to model generic language phenomena. Furthermore, we describe an extension that uses a mixture of output distributions from all learned styles to perform on-the fly style adaptation based on the textual input alone. Experimentally, we find that the proposed models consistently outperform models that encapsulate single-style or average-style language generation capabilities.
Tasks	Text Generation
Published	2018-04-11
URL	http://arxiv.org/abs/1804.04093v1
PDF	http://arxiv.org/pdf/1804.04093v1.pdf
PWC	https://paperswithcode.com/paper/shaped-shared-private-encoder-decoder-for
Repo
Framework

Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation


Title	Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation
Authors	Lucas Vinh Tran, Tuan-Anh Nguyen Pham, Yi Tay, Yiding Liu, Gao Cong, Xiaoli Li
Abstract	This paper proposes Medley of Sub-Attention Networks (MoSAN), a new novel neural architecture for the group recommendation task. Group-level recommendation is known to be a challenging task, in which intricate group dynamics have to be considered. As such, this is to be contrasted with the standard recommendation problem where recommendations are personalized with respect to a single user. Our proposed approach hinges upon the key intuition that the decision making process (in groups) is generally dynamic, i.e., a user’s decision is highly dependent on the other group members. All in all, our key motivation manifests in a form of an attentive neural model that captures fine-grained interactions between group members. In our MoSAN model, each sub-attention module is representative of a single member, which models a user’s preference with respect to all other group members. Subsequently, a Medley of Sub-Attention modules is then used to collectively make the group’s final decision. Overall, our proposed model is both expressive and effective. Via a series of extensive experiments, we show that MoSAN not only achieves state-of-the-art performance but also improves standard baselines by a considerable margin.
Tasks	Decision Making
Published	2018-04-12
URL	https://arxiv.org/abs/1804.04327v5
PDF	https://arxiv.org/pdf/1804.04327v5.pdf
PWC	https://paperswithcode.com/paper/attention-based-group-recommendation
Repo
Framework

Training Medical Image Analysis Systems like Radiologists


Title	Training Medical Image Analysis Systems like Radiologists
Authors	Gabriel Maicas, Andrew P. Bradley, Jacinto C. Nascimento, Ian Reid, Gustavo Carneiro
Abstract	The training of medical image analysis systems using machine learning approaches follows a common script: collect and annotate a large dataset, train the classifier on the training set, and test it on a hold-out test set. This process bears no direct resemblance with radiologist training, which is based on solving a series of tasks of increasing difficulty, where each task involves the use of significantly smaller datasets than those used in machine learning. In this paper, we propose a novel training approach inspired by how radiologists are trained. In particular, we explore the use of meta-training that models a classifier based on a series of tasks. Tasks are selected using teacher-student curriculum learning, where each task consists of simple classification problems containing small training sets. We hypothesize that our proposed meta-training approach can be used to pre-train medical image analysis models. This hypothesis is tested on the automatic breast screening classification from DCE-MRI trained with weakly labeled datasets. The classification performance achieved by our approach is shown to be the best in the field for that application, compared to state of art baseline approaches: DenseNet, multiple instance learning and multi-task learning.
Tasks	Multiple Instance Learning, Multi-Task Learning
Published	2018-05-28
URL	http://arxiv.org/abs/1805.10884v3
PDF	http://arxiv.org/pdf/1805.10884v3.pdf
PWC	https://paperswithcode.com/paper/training-medical-image-analysis-systems-like
Repo
Framework

Structured Pruning of Neural Networks with Budget-Aware Regularization


Title	Structured Pruning of Neural Networks with Budget-Aware Regularization
Authors	Carl Lemaire, Andrew Achkar, Pierre-Marc Jodoin
Abstract	Pruning methods have shown to be effective at reducing the size of deep neural networks while keeping accuracy almost intact. Among the most effective methods are those that prune a network while training it with a sparsity prior loss and learnable dropout parameters. A shortcoming of these approaches however is that neither the size nor the inference speed of the pruned network can be controlled directly; yet this is a key feature for targeting deployment of CNNs on low-power hardware. To overcome this, we introduce a budgeted regularized pruning framework for deep CNNs. Our approach naturally fits into traditional neural network training as it consists of a learnable masking layer, a novel budget-aware objective function, and the use of knowledge distillation. We also provide insights on how to prune a residual network and how this can lead to new architectures. Experimental results reveal that CNNs pruned with our method are more accurate and less compute-hungry than state-of-the-art methods. Also, our approach is more effective at preventing accuracy collapse in case of severe pruning; this allows us to attain pruning factors up to 16x without significant accuracy drop.
Tasks
Published	2018-11-23
URL	https://arxiv.org/abs/1811.09332v3
PDF	https://arxiv.org/pdf/1811.09332v3.pdf
PWC	https://paperswithcode.com/paper/structured-pruning-of-neural-networks-with
Repo
Framework

Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network


Title	Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network
Authors	Amarjot Singh, Devendra Patil, SN Omkar
Abstract	Drone systems have been deployed by various law enforcement agencies to monitor hostiles, spy on foreign drug cartels, conduct border control operations, etc. This paper introduces a real-time drone surveillance system to identify violent individuals in public areas. The system first uses the Feature Pyramid Network to detect humans from aerial images. The image region with the human is used by the proposed ScatterNet Hybrid Deep Learning (SHDL) network for human pose estimation. The orientations between the limbs of the estimated pose are next used to identify the violent individuals. The proposed deep network can learn meaningful representations quickly using ScatterNet and structural priors with relatively fewer labeled examples. The system detects the violent individuals in real-time by processing the drone images in the cloud. This research also introduces the aerial violent individual dataset used for training the deep network which hopefully may encourage researchers interested in using deep learning for aerial surveillance. The pose estimation and violent individuals identification performance is compared with the state-of-the-art techniques.
Tasks	Pose Estimation
Published	2018-06-03
URL	http://arxiv.org/abs/1806.00746v1
PDF	http://arxiv.org/pdf/1806.00746v1.pdf
PWC	https://paperswithcode.com/paper/eye-in-the-sky-real-time-drone-surveillance
Repo
Framework

Distribution Matching in Variational Inference


Title	Distribution Matching in Variational Inference
Authors	Mihaela Rosca, Balaji Lakshminarayanan, Shakir Mohamed
Abstract	With the increasingly widespread deployment of generative models, there is a mounting need for a deeper understanding of their behaviors and limitations. In this paper, we expose the limitations of Variational Autoencoders (VAEs), which consistently fail to learn marginal distributions in both latent and visible spaces. We show this to be a consequence of learning by matching conditional distributions, and the limitations of explicit model and posterior distributions. It is popular to consider Generative Adversarial Networks (GANs) as a means of overcoming these limitations, leading to hybrids of VAEs and GANs. We perform a large-scale evaluation of several VAE-GAN hybrids and analyze the implications of class probability estimation for learning distributions. While promising, we conclude that at present, VAE-GAN hybrids have limited applicability: they are harder to scale, evaluate, and use for inference compared to VAEs; and they do not improve over the generation quality of GANs.
Tasks
Published	2018-02-19
URL	https://arxiv.org/abs/1802.06847v4
PDF	https://arxiv.org/pdf/1802.06847v4.pdf
PWC	https://paperswithcode.com/paper/distribution-matching-in-variational
Repo
Framework

Safe Reinforcement Learning with Model Uncertainty Estimates


Title	Safe Reinforcement Learning with Model Uncertainty Estimates
Authors	Björn Lütjens, Michael Everett, Jonathan P. How
Abstract	Many current autonomous systems are being designed with a strong reliance on black box predictions from deep neural networks (DNNs). However, DNNs tend to be overconfident in predictions on unseen data and can give unpredictable results for far-from-distribution test data. The importance of predictions that are robust to this distributional shift is evident for safety-critical applications, such as collision avoidance around pedestrians. Measures of model uncertainty can be used to identify unseen data, but the state-of-the-art extraction methods such as Bayesian neural networks are mostly intractable to compute. This paper uses MC-Dropout and Bootstrapping to give computationally tractable and parallelizable uncertainty estimates. The methods are embedded in a Safe Reinforcement Learning framework to form uncertainty-aware navigation around pedestrians. The result is a collision avoidance policy that knows what it does not know and cautiously avoids pedestrians that exhibit unseen behavior. The policy is demonstrated in simulation to be more robust to novel observations and take safer actions than an uncertainty-unaware baseline.
Tasks
Published	2018-10-19
URL	http://arxiv.org/abs/1810.08700v2
PDF	http://arxiv.org/pdf/1810.08700v2.pdf
PWC	https://paperswithcode.com/paper/safe-reinforcement-learning-with-model
Repo
Framework

Smoothed Online Convex Optimization in High Dimensions via Online Balanced Descent


Title	Smoothed Online Convex Optimization in High Dimensions via Online Balanced Descent
Authors	Niangjun Chen, Gautam Goel, Adam Wierman
Abstract	We study Smoothed Online Convex Optimization, a version of online convex optimization where the learner incurs a penalty for changing her actions between rounds. Given a $\Omega(\sqrt{d})$ lower bound on the competitive ratio of any online algorithm, where $d$ is the dimension of the action space, we ask under what conditions this bound can be beaten. We introduce a novel algorithmic framework for this problem, Online Balanced Descent (OBD), which works by iteratively projecting the previous point onto a carefully chosen level set of the current cost function so as to balance the switching costs and hitting costs. We demonstrate the generality of the OBD framework by showing how, with different choices of “balance,” OBD can improve upon state-of-the-art performance guarantees for both competitive ratio and regret, in particular, OBD is the first algorithm to achieve a dimension-free competitive ratio, $3 + O(1/\alpha)$, for locally polyhedral costs, where $\alpha$ measures the “steepness” of the costs. We also prove bounds on the dynamic regret of OBD when the balance is performed in the dual space that are dimension-free and imply that OBD has sublinear static regret.
Tasks
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10366v2
PDF	http://arxiv.org/pdf/1803.10366v2.pdf
PWC	https://paperswithcode.com/paper/smoothed-online-convex-optimization-in-high
Repo
Framework