January 30, 2020

3466 words 17 mins read

Paper Group ANR 300

Partner Approximating Learners (PAL): Simulation-Accelerated Learning with Explicit Partner Modeling in Multi-Agent Domains. How a minimal learning agent can infer the existence of unobserved variables in a complex environment. Do Lateral Views Help Automated Chest X-ray Predictions?. Variable Population Memetic Search: A Case Study on the Critical …

Partner Approximating Learners (PAL): Simulation-Accelerated Learning with Explicit Partner Modeling in Multi-Agent Domains


Title	Partner Approximating Learners (PAL): Simulation-Accelerated Learning with Explicit Partner Modeling in Multi-Agent Domains
Authors	Florian Köpf, Alexander Nitsch, Michael Flad, Sören Hohmann
Abstract	Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning agents. In order to contribute towards intuitive human-machine collaboration, we focus on problems in the continuous state and control domain where no explicit communication is considered and the agents do not know the others’ goals or control laws but only sense their control inputs retrospectively. Our proposed framework combines a learned partner model based on online data with a reinforcement learning agent that is trained in a simulated environment including the partner model. Thus, we overcome drawbacks of independent learners and, in addition, benefit from a reduced amount of real world data required for reinforcement learning which is vital in the human-machine context. We finally analyze an example that demonstrates the merits of our proposed framework which learns fast due to the simulated environment and adapts to the continuously changing partner due to the partner approximation.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03868v3
PDF	https://arxiv.org/pdf/1909.03868v3.pdf
PWC	https://paperswithcode.com/paper/partner-approximating-learners-pal-simulation
Repo
Framework

How a minimal learning agent can infer the existence of unobserved variables in a complex environment


Title	How a minimal learning agent can infer the existence of unobserved variables in a complex environment
Authors	Katja Ried, Benjamin Eva, Thomas Müller, Hans J. Briegel
Abstract	According to a mainstream position in contemporary cognitive science and philosophy, the use of abstract compositional concepts is both a necessary and a sufficient condition for the presence of genuine thought. In this article, we show how the ability to develop and utilise abstract conceptual structures can be achieved by a particular kind of learning agents. More specifically, we provide and motivate a concrete operational definition of what it means for these agents to be in possession of abstract concepts, before presenting an explicit example of a minimal architecture that supports this capability. We then proceed to demonstrate how the existence of abstract conceptual structures can be operationally useful in the process of employing previously acquired knowledge in the face of new experiences, thereby vindicating the natural conjecture that the cognitive functions of abstraction and generalisation are closely related. Keywords: concept formation, projective simulation, reinforcement learning, transparent artificial intelligence, theory formation, explainable artificial intelligence (XAI)
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06985v1
PDF	https://arxiv.org/pdf/1910.06985v1.pdf
PWC	https://paperswithcode.com/paper/how-a-minimal-learning-agent-can-infer-the
Repo
Framework

Do Lateral Views Help Automated Chest X-ray Predictions?


Title	Do Lateral Views Help Automated Chest X-ray Predictions?
Authors	Hadrien Bertrand, Mohammad Hashir, Joseph Paul Cohen
Abstract	Most convolutional neural networks in chest radiology use only the frontal posteroanterior (PA) view to make a prediction. However the lateral view is known to help the diagnosis of certain diseases and conditions. The recently released PadChest dataset contains paired PA and lateral views, allowing us to study for which diseases and conditions the performance of a neural network improves when provided a lateral x-ray view as opposed to a frontal posteroanterior (PA) view. Using a simple DenseNet model, we find that using the lateral view increases the AUC of 8 of the 56 labels in our data and achieves the same performance as the PA view for 21 of the labels. We find that using the PA and lateral views jointly doesn’t trivially lead to an increase in performance but suggest further investigation.
Tasks
Published	2019-04-17
URL	https://arxiv.org/abs/1904.08534v2
PDF	https://arxiv.org/pdf/1904.08534v2.pdf
PWC	https://paperswithcode.com/paper/do-lateral-views-help-automated-chest-x-ray
Repo
Framework

Variable Population Memetic Search: A Case Study on the Critical Node Problem


Title	Variable Population Memetic Search: A Case Study on the Critical Node Problem
Authors	Yangming Zhou, Jin-Kao Hao, Zhang-Hua Fu, Zhe Wang, Xiangjing Lai
Abstract	Population-based memetic algorithms have been successfully applied to solve many difficult combinatorial problems. Often, a population of fixed size was used in such algorithms to record some best solutions sampled during the search. However, given the particular features of the problem instance under consideration, a population of variable size would be more suitable to ensure the best search performance possible. In this work, we propose variable population memetic search (VPMS), where a strategic population sizing mechanism is used to dynamically adjust the population size during the memetic search process. Our VPMS approach starts its search from a small population of only two solutions to focus on exploitation, and then adapts the population size according to the search status to continuously influence the balancing between exploitation and exploration. We illustrate an application of the VPMS approach to solve the challenging critical node problem (CNP). We show that the VPMS algorithm integrating a variable population, an effective local optimization procedure (called diversified late acceptance search) and a backbone-based crossover operator performs very well compared to state-of-the-art CNP algorithms. The algorithm is able to discover new upper bounds for 13 instances out of the 42 popular benchmark instances, while matching 23 previous best-known upper bounds.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.08691v1
PDF	https://arxiv.org/pdf/1909.08691v1.pdf
PWC	https://paperswithcode.com/paper/variable-population-memetic-search-a-case
Repo
Framework

Trepan Reloaded: A Knowledge-driven Approach to Explaining Artificial Neural Networks


Title	Trepan Reloaded: A Knowledge-driven Approach to Explaining Artificial Neural Networks
Authors	Roberto Confalonieri, Tillman Weyde, Tarek R. Besold, Fermín Moscoso del Prado Martín
Abstract	Explainability in Artificial Intelligence has been revived as a topic of active research by the need of conveying safety and trust to users in the `how' and` why’ of automated decision-making. Whilst a plethora of approaches have been developed for post-hoc explainability, only a few focus on how to use domain knowledge, and how this influences the understandability of global explanations from the users’ perspective. In this paper, we show how ontologies help the understandability of global post-hoc explanations, presented in the form of symbolic models. In particular, we build on Trepan, an algorithm that explains artificial neural networks by means of decision trees, and we extend it to include ontologies modeling domain knowledge in the process of generating explanations. We present the results of a user study that measures the understandability of decision trees using a syntactic complexity measure, and through time and accuracy of responses as well as reported user confidence and understandability. The user study considers domains where explanations are critical, namely, in finance and medicine. The results show that decision trees generated with our algorithm, taking into account domain knowledge, are more understandable than those generated by standard Trepan without the use of ontologies.
Tasks	Decision Making, Interpretable Machine Learning
Published	2019-06-19
URL	https://arxiv.org/abs/1906.08362v2
PDF	https://arxiv.org/pdf/1906.08362v2.pdf
PWC	https://paperswithcode.com/paper/an-ontology-based-approach-to-explaining
Repo
Framework

FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals


Title	FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
Authors	Umur Aybars Ciftci, Ilke Demir
Abstract	We present a novel approach to detect synthetic content in portrait videos, as a preventive solution for the emerging threat of deep fakes. In other words, we introduce a deep fake detector. We observe that detectors blindly utilizing deep learning are not effective in catching fake content, as generative models produce formidably realistic results. Our key assertion follows that biological signals hidden in portrait videos can be used as an implicit descriptor of authenticity, because they are neither spatially nor temporally preserved in fake content. To prove and exploit this assertion, we first exhibit several unary and binary signal transformations for the pairwise separation problem, achieving 99.39% accuracy. Second, we utilize those findings to formulate a generalized classifier for fake content, by analyzing proposed signal transformations and corresponding feature sets. Third, we generate novel signal maps and employ a CNN to improve our traditional classifier for detecting synthetic content. Lastly, we release an “in the wild” dataset of fake portrait videos that we collected as a part of our evaluation process. We evaluate FakeCatcher both on Face Forensics dataset and on our new Deep Fakes dataset, performing with 96% and 91.07% accuracies respectively. In addition, our approach produces a significantly superior detection rate against baselines, and does not depend on the source, generator, or properties of the fake content. We also analyze signals from various facial regions, with varying segment durations, and under several dimensionality reduction techniques.
Tasks	Dimensionality Reduction, Video Compression
Published	2019-01-08
URL	https://arxiv.org/abs/1901.02212v2
PDF	https://arxiv.org/pdf/1901.02212v2.pdf
PWC	https://paperswithcode.com/paper/fakecatcher-detection-of-synthetic-portrait
Repo
Framework

Graphlets in Multiplex Networks


Title	Graphlets in Multiplex Networks
Authors	Tamara Dimitrova, Kristijan Petrovski, Ljupco Kocarev
Abstract	We develop graphlet analysis for multiplex networks and discuss how this analysis can be extended to multilayer and multilevel networks as well as to graphs with node and/or link categorical attributes. The analysis has been adapted for two typical examples of multiplexes: economic trade data represented as a 957-plex network and 75 social networks each represented as a 12-plex network. We show that wedges (open triads) occur more often in economic trade networks than in social networks, indicating the tendency of a country to produce/trade of a product in local structure of triads which are not closed. Moreover, our analysis provides evidence that the countries with small diversity tend to form correlated triangles. Wedges also appear in the social networks, however the dominant graphlets in social networks are triangles (closed triads). If a multiplex structure indicates a strong tie, the graphlet analysis provides another evidence for the concepts of strong/weak ties and structural holes. In contrast to Granovetter’s seminal work on the strength of weak ties, in which it has been documented that the wedges with only strong ties are absent, here we show that for the analyzed 75 social networks, the wedges with only strong ties are not only present but also significantly correlated.
Tasks
Published	2019-11-17
URL	https://arxiv.org/abs/1912.08930v1
PDF	https://arxiv.org/pdf/1912.08930v1.pdf
PWC	https://paperswithcode.com/paper/graphlets-in-multiplex-networks
Repo
Framework

Towards Visually Explaining Variational Autoencoders


Title	Towards Visually Explaining Variational Autoencoders
Authors	Wenqian Liu, Runze Li, Meng Zheng, Srikrishna Karanam, Ziyan Wu, Bir Bhanu, Richard J. Radke, Octavia Camps
Abstract	Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have driven much recent effort in using visual attention maps as a means for visual explanations. A key problem, however, is these methods are designed for classification and categorization tasks, and their extension to explaining generative models, e.g. variational autoencoders (VAE) is not trivial. In this work, we take a step towards bridging this crucial gap, proposing the first technique to visually explain VAEs by means of gradient-based attention. We present methods to generate visual attention from the learned latent space, and also demonstrate such attention explanations serve more than just explaining VAE predictions. We show how these attention maps can be used to localize anomalies in images, demonstrating state-of-the-art performance on the MVTec-AD dataset. We also show how they can be infused into model training, helping bootstrap the VAE into learning improved latent space disentanglement, demonstrated on the Dsprites dataset.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07389v6
PDF	https://arxiv.org/pdf/1911.07389v6.pdf
PWC	https://paperswithcode.com/paper/towards-visually-explaining-variational
Repo
Framework

A hybrid machine learning framework for analyzing human decision making through learning preferences


Title	A hybrid machine learning framework for analyzing human decision making through learning preferences
Authors	Mengzhuo Guo, Qingpeng Zhang, Xiuwu Liao, Frank Youhua Chen, Daniel Dajun Zeng
Abstract	Machine learning has recently been widely adopted to address the managerial decision making problems, in which the decision maker needs to be able to interpret the contributions of individual attributes in an explicit form. However, there is a trade-off between performance and interpretability. Full complexity models are non-traceable black-box, whereas classic interpretable models are usually simplified with lower accuracy. This trade-off limits the application of state-of-the-art machine learning models in management problems, which requires high prediction performance, as well as the understanding of individual attributes’ contributions to the model outcome. Multiple criteria decision aiding (MCDA) is a family of analytic approaches to depicting the rationale of human decision. It is also limited by strong assumptions. To meet the decision maker’s demand for more interpretable machine learning models, we propose a novel hybrid method, namely Neural Network-based Multiple Criteria Decision Aiding, which combines an additive value model and a fully-connected multilayer perceptron (MLP) to achieve good performance while capturing the explicit relationships between individual attributes and the prediction. NN-MCDA has a linear component to characterize such relationships through providing explicit marginal value functions, and a nonlinear component to capture the implicit high-order interactions between attributes and their complex nonlinear transformations. We demonstrate the effectiveness of NN-MCDA with extensive simulation studies and three real-world datasets. To the best of our knowledge, this research is the first to enhance the interpretability of machine learning models with MCDA techniques. The proposed framework also sheds light on how to use machine learning techniques to free MCDA from strong assumptions.
Tasks	Decision Making, Interpretable Machine Learning
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01233v3
PDF	https://arxiv.org/pdf/1906.01233v3.pdf
PWC	https://paperswithcode.com/paper/an-interpretable-machine-learning-framework
Repo
Framework

EDUQA: Educational Domain Question Answering System using Conceptual Network Mapping


Title	EDUQA: Educational Domain Question Answering System using Conceptual Network Mapping
Authors	Abhishek Agarwal, Nikhil Sachdeva, Raj Kamal Yadav, Vishaal Udandarao, Vrinda Mittal, Anubha Gupta, Abhinav Mathur
Abstract	Most of the existing question answering models can be largely compiled into two categories: i) open domain question answering models that answer generic questions and use large-scale knowledge base along with the targeted web-corpus retrieval and ii) closed domain question answering models that address focused questioning area and use complex deep learning models. Both the above models derive answers through textual comprehension methods. Due to their inability to capture the pedagogical meaning of textual content, these models are not appropriately suited to the educational field for pedagogy. In this paper, we propose an on-the-fly conceptual network model that incorporates educational semantics. The proposed model preserves correlations between conceptual entities by applying intelligent indexing algorithms on the concept network so as to improve answer generation. This model can be utilized for building interactive conversational agents for aiding classroom learning.
Tasks	Open-Domain Question Answering, Question Answering
Published	2019-11-12
URL	https://arxiv.org/abs/1911.05013v1
PDF	https://arxiv.org/pdf/1911.05013v1.pdf
PWC	https://paperswithcode.com/paper/eduqa-educational-domain-question-answering
Repo
Framework

Hybrid Predictive Model: When an Interpretable Model Collaborates with a Black-box Model


Title	Hybrid Predictive Model: When an Interpretable Model Collaborates with a Black-box Model
Authors	Tong Wang, Qihang Lin
Abstract	Interpretable machine learning has become a strong competitor for traditional black-box models. However, the possible loss of the predictive performance for gaining interpretability is often inevitable, putting practitioners in a dilemma of choosing between high accuracy (black-box models) and interpretability (interpretable models). In this work, we propose a novel framework for building a Hybrid Predictive Model (HPM) that integrates an interpretable model with any black-box model to combine their strengths. The interpretable model substitutes the black-box model on a subset of data where the black-box is overkill or nearly overkill, gaining transparency at no or low cost of the predictive accuracy. We design a principled objective function that considers predictive accuracy, model interpretability, and model transparency (defined as the percentage of data processed by the interpretable substitute.) Under this framework, we propose two hybrid models, one substituting with association rules and the other with linear models, and we design customized training algorithms for both models. We test the hybrid models on structured data and text data where interpretable models collaborate with various state-of-the-art black-box models. Results show that hybrid models obtain an efficient trade-off between transparency and predictive performance, characterized by our proposed efficient frontiers.
Tasks	Interpretable Machine Learning
Published	2019-05-10
URL	https://arxiv.org/abs/1905.04241v1
PDF	https://arxiv.org/pdf/1905.04241v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-predictive-model-when-an-interpretable
Repo
Framework

Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization


Title	Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization
Authors	Manirupa Das, Juanxi Li, Eric Fosler-Lussier, Simon Lin, Soheil Moosavinasab, Steve Rust, Yungui Huang, Rajiv Ramnath
Abstract	Novel contexts may often arise in complex querying scenarios such as in evidence-based medicine (EBM) involving biomedical literature, that may not explicitly refer to entities or canonical concept forms occurring in any fact- or rule-based knowledge source such as an ontology like the UMLS. Moreover, hidden associations between candidate concepts meaningful in the current context, may not exist within a single document, but within the collection, via alternate lexical forms. Therefore, inspired by the recent success of sequence-to-sequence neural models in delivering the state-of-the-art in a wide range of NLP tasks, we develop a novel sequence-to-set framework with neural attention for learning document representations that can effect term transfer within the corpus, for semantically tagging a large collection of documents. We demonstrate that our proposed method can be effective in both a supervised multi-label classification setup for text categorization, as well as in a unique unsupervised setting with no human-annotated document labels that uses no external knowledge resources and only corpus-derived term statistics to drive the training. Further, we show that semi-supervised training using our architecture on large amounts of unlabeled data can augment performance on the text categorization task when limited labeled data is available. Our approach to generate document encodings employing our sequence-to-set models for inference of semantic tags, gives to the best of our knowledge, the state-of-the-art for both, the unsupervised query expansion task for the TREC CDS 2016 challenge dataset when evaluated on an Okapi BM25–based document retrieval system; and also over the MLTM baseline (Soleimani et al, 2016), for both supervised and semi-supervised multi-label prediction tasks on the del.icio.us and Ohsumed datasets. We will make our code and data publicly available.
Tasks	Multi-Label Classification, Text Categorization
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04427v1
PDF	https://arxiv.org/pdf/1911.04427v1.pdf
PWC	https://paperswithcode.com/paper/sequence-to-set-semantic-tagging-end-to-end
Repo
Framework

Variance reduction for MCMC methods via martingale representations


Title	Variance reduction for MCMC methods via martingale representations
Authors	D. Belomestny, E. Moulines, N. Shagadatov, M. Urusov
Abstract	In this paper we propose an efficient variance reduction approach for MCMC algorithms relying on a novel discrete time martingale representation for Markov chains. Our approach is fully non-asymptotic and does not require any type of ergodicity or special product structure of the underlying density. By rigorously analyzing the convergence of the proposed algorithm, we show that it’s complexity is indeed significantly smaller than one of the original MCMC algorithm. The numerical performance of the new method is illustrated in the case of Gaussian mixtures and binary regression.
Tasks
Published	2019-03-18
URL	https://arxiv.org/abs/1903.07373v2
PDF	https://arxiv.org/pdf/1903.07373v2.pdf
PWC	https://paperswithcode.com/paper/variance-reduction-for-mcmc-methods-via
Repo
Framework

Aspect Specific Opinion Expression Extraction using Attention based LSTM-CRF Network


Title	Aspect Specific Opinion Expression Extraction using Attention based LSTM-CRF Network
Authors	Abhishek Laddha, Arjun Mukherjee
Abstract	Opinion phrase extraction is one of the key tasks in fine-grained sentiment analysis. While opinion expressions could be generic subjective expressions, aspect specific opinion expressions contain both the aspect as well as the opinion expression within the original sentence context. In this work, we formulate the task as an instance of token-level sequence labeling. When multiple aspects are present in a sentence, detection of opinion phrase boundary becomes difficult and label of each word depend not only upon the surrounding words but also with the concerned aspect. We propose a neural network architecture with bidirectional LSTM (Bi-LSTM) and a novel attention mechanism. Bi-LSTM layer learns the various sequential pattern among the words without requiring any hand-crafted features. The attention mechanism captures the importance of context words on a particular aspect opinion expression when multiple aspects are present in a sentence via location and content based memory. A Conditional Random Field (CRF) model is incorporated in the final layer to explicitly model the dependencies among the output labels. Experimental results on Hotel dataset from Tripadvisor.com showed that our approach outperformed several state-of-the-art baselines.
Tasks	Sentiment Analysis
Published	2019-02-07
URL	http://arxiv.org/abs/1902.02709v1
PDF	http://arxiv.org/pdf/1902.02709v1.pdf
PWC	https://paperswithcode.com/paper/aspect-specific-opinion-expression-extraction
Repo
Framework

Non-monotone DR-submodular Maximization: Approximation and Regret Guarantees


Title	Non-monotone DR-submodular Maximization: Approximation and Regret Guarantees
Authors	Christoph Dürr, Nguyen Kim Thang, Abhinav Srivastav, Léo Tible
Abstract	Diminishing-returns (DR) submodular optimization is an important field with many real-world applications in machine learning, economics and communication systems. It captures a subclass of non-convex optimization that provides both practical and theoretical guarantees. In this paper, we study the fundamental problem of maximizing non-monotone DR-submodular functions over down-closed and general convex sets in both offline and online settings. First, we show that for offline maximizing non-monotone DR-submodular functions over a general convex set, the Frank-Wolfe algorithm achieves an approximation guarantee which depends on the convex set. Next, we show that the Stochastic Gradient Ascent algorithm achieves a 1/4-approximation ratio with the regret of $O(1/\sqrt{T})$ for the problem of maximizing non-monotone DR-submodular functions over down-closed convex sets. These are the first approximation guarantees in the corresponding settings. Finally we benchmark these algorithms on problems arising in machine learning domain with the real-world datasets.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09595v1
PDF	https://arxiv.org/pdf/1905.09595v1.pdf
PWC	https://paperswithcode.com/paper/non-monotone-dr-submodular-maximization
Repo
Framework