Paper Group ANR 1267
Active Automata Learning with Adaptive Distinguishing Sequences. A Deep Reinforcement Learning Approach to Multi-component Job Scheduling in Edge Computing. Latent Space Reinforcement Learning for Steering Angle Prediction. On the geometry of Stein variational gradient descent. Forecasting Future Action Sequences with Neural Memory Networks. Cluste …
Active Automata Learning with Adaptive Distinguishing Sequences
| Title | Active Automata Learning with Adaptive Distinguishing Sequences |
| Authors | Markus Theo Frohme |
| Abstract | This document investigates the integration of adaptive distinguishing sequences into the process of active automata learning (AAL). A novel AAL algorithm “ADT” (adaptive discrimination tree) is developed and presented. Since the submission of the original thesis, the presented algorithm has been integrated into LearnLib - an open-source library for active automata learning - and has been successfully used in related fields of research. |
| Tasks | |
| Published | 2019-02-04 |
| URL | http://arxiv.org/abs/1902.01139v1 |
| http://arxiv.org/pdf/1902.01139v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-automata-learning-with-adaptive |
| Repo | |
| Framework | |
A Deep Reinforcement Learning Approach to Multi-component Job Scheduling in Edge Computing
| Title | A Deep Reinforcement Learning Approach to Multi-component Job Scheduling in Edge Computing |
| Authors | Zhi Cao, Honggang Zhang, Yu Cao, Benyuan Liu |
| Abstract | We are interested in the optimal scheduling of a collection of multi-component application jobs in an edge computing system that consists of geo-distributed edge computing nodes connected through a wide area network. The scheduling and placement of application jobs in an edge system is challenging due to the interdependence of multiple components of each job, and the communication delays between the geographically distributed data sources and edge nodes and their dynamic availability. In this paper we explore the feasibility of applying Deep Reinforcement Learning (DRL) based design to address these challenges. We introduce a DRL actor-critic algorithm that aims to find an optimal scheduling policy to minimize average job slowdown in the edge system. We have demonstrated through simulations that our design outperforms a few existing algorithms, based on both synthetic data and a Google cloud data trace. |
| Tasks | |
| Published | 2019-08-26 |
| URL | https://arxiv.org/abs/1908.10290v3 |
| https://arxiv.org/pdf/1908.10290v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-reinforcement-learning-approach-to |
| Repo | |
| Framework | |
Latent Space Reinforcement Learning for Steering Angle Prediction
| Title | Latent Space Reinforcement Learning for Steering Angle Prediction |
| Authors | Qadeer Khan, Torsten Schön, Patrick Wenzel |
| Abstract | Model-free reinforcement learning has recently been shown to successfully learn navigation policies from raw sensor data. In this work, we address the problem of learning driving policies for an autonomous agent in a high-fidelity simulator. Building upon recent research that applies deep reinforcement learning to navigation problems, we present a modular deep reinforcement learning approach to predict the steering angle of the car from raw images. The first module extracts a low-dimensional latent semantic representation of the image. The control module trained with reinforcement learning takes the latent vector as input to predict the correct steering angle. The experimental results have showed that our method is capable of learning to maneuver the car without any human control signals. |
| Tasks | |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.03765v1 |
| http://arxiv.org/pdf/1902.03765v1.pdf | |
| PWC | https://paperswithcode.com/paper/latent-space-reinforcement-learning-for |
| Repo | |
| Framework | |
On the geometry of Stein variational gradient descent
| Title | On the geometry of Stein variational gradient descent |
| Authors | A. Duncan, N. Nuesken, L. Szpruch |
| Abstract | Bayesian inference problems require sampling or approximating high-dimensional probability distributions. The focus of this paper is on the recently introduced Stein variational gradient descent methodology, a class of algorithms that rely on iterated steepest descent steps with respect to a reproducing kernel Hilbert space norm. This construction leads to interacting particle systems, the mean-field limit of which is a gradient flow on the space of probability distributions equipped with a certain geometrical structure. We leverage this viewpoint to shed some light on the convergence properties of the algorithm, in particular addressing the problem of choosing a suitable positive definite kernel function. Our analysis leads us to considering certain nondifferentiable kernels with adjusted tails. We demonstrate significant performs gains of these in various numerical experiments. |
| Tasks | Bayesian Inference |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00894v1 |
| https://arxiv.org/pdf/1912.00894v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-geometry-of-stein-variational-gradient |
| Repo | |
| Framework | |
Forecasting Future Action Sequences with Neural Memory Networks
| Title | Forecasting Future Action Sequences with Neural Memory Networks |
| Authors | Harshala Gammulle, Simon Denman, Sridha Sridharan, Clinton Fookes |
| Abstract | We propose a novel neural memory network based framework for future action sequence forecasting. This is a challenging task where we have to consider short-term, within sequence relationships as well as relationships in between sequences, to understand how sequences of actions evolve over time. To capture these relationships effectively, we introduce neural memory networks to our modelling scheme. We show the significance of using two input streams, the observed frames and the corresponding action labels, which provide different information cues for our prediction task. Furthermore, through the proposed method we effectively map the long-term relationships among individual input sequences through separate memory modules, which enables better fusion of the salient features. Our method outperforms the state-of-the-art approaches by a large margin on two publicly available datasets: Breakfast and 50 Salads. |
| Tasks | |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09278v1 |
| https://arxiv.org/pdf/1909.09278v1.pdf | |
| PWC | https://paperswithcode.com/paper/forecasting-future-action-sequences-with |
| Repo | |
| Framework | |
Clustering via Ant Colonies: Parameter Analysis and Improvement of the Algorithm
| Title | Clustering via Ant Colonies: Parameter Analysis and Improvement of the Algorithm |
| Authors | Jeffry Chavarria-Molina, Juan Jose Fallas-Monge, Javier Trejos-Zelaya |
| Abstract | An ant colony optimization approach for partitioning a set of objects is proposed. In order to minimize the intra-variance, or within sum-of-squares, of the partitioned classes, we construct ant-like solutions by a constructive approach that selects objects to be put in a class with a probability that depends on the distance between the object and the centroid of the class (visibility) and the pheromone trail; the latter depends on the class memberships that have been defined along the iterations. The procedure is improved with the application of K-means algorithm in some iterations of the ant colony method. We performed a simulation study in order to evaluate the method with a Monte Carlo experiment that controls some sensitive parameters of the clustering problem. After some tuning of the parameters, the method has also been applied to some benchmark real-data sets. Encouraging results were obtained in nearly all cases. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.01105v1 |
| https://arxiv.org/pdf/1912.01105v1.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-via-ant-colonies-parameter |
| Repo | |
| Framework | |
Universal Approximation of Input-Output Maps by Temporal Convolutional Nets
| Title | Universal Approximation of Input-Output Maps by Temporal Convolutional Nets |
| Authors | Joshua Hanson, Maxim Raginsky |
| Abstract | There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive performance. For systems having limited long-term temporal dependencies, the approximation capability of recurrent networks is essentially equivalent to that of temporal convolutional nets (TCNs). We prove that TCNs can approximate a large class of input-output maps having approximately finite memory to arbitrary error tolerance. Furthermore, we derive quantitative approximation rates for deep ReLU TCNs in terms of the width and depth of the network and modulus of continuity of the original input-output map, and apply these results to input-output maps of systems that admit finite-dimensional state-space realizations (i.e., recurrent models). |
| Tasks | |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09211v2 |
| https://arxiv.org/pdf/1906.09211v2.pdf | |
| PWC | https://paperswithcode.com/paper/universal-approximation-of-input-output-maps |
| Repo | |
| Framework | |
On Multi-Agent Learning in Team Sports Games
| Title | On Multi-Agent Learning in Team Sports Games |
| Authors | Yunqi Zhao, Igor Borovikov, Jason Rupert, Caedmon Somers, Ahmad Beirami |
| Abstract | In recent years, reinforcement learning has been successful in solving video games from Atari to Star Craft II. However, the end-to-end model-free reinforcement learning (RL) is not sample efficient and requires a significant amount of computational resources to achieve superhuman level performance. Model-free RL is also unlikely to produce human-like agents for playtesting and gameplaying AI in the development cycle of complex video games. In this paper, we present a hierarchical approach to training agents with the goal of achieving human-like style and high skill level in team sports games. While this is still work in progress, our preliminary results show that the presented approach holds promise for solving the posed multi-agent learning problem. |
| Tasks | |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10124v1 |
| https://arxiv.org/pdf/1906.10124v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-multi-agent-learning-in-team-sports-games |
| Repo | |
| Framework | |
On the Effectiveness of Laser Speckle Contrast Imaging and Deep Neural Networks for Detecting Known and Unknown Fingerprint Presentation Attacks
| Title | On the Effectiveness of Laser Speckle Contrast Imaging and Deep Neural Networks for Detecting Known and Unknown Fingerprint Presentation Attacks |
| Authors | Hengameh Mirzaalian, Mohamed Hussein, Wael Abd-Almageed |
| Abstract | Fingerprint presentation attack detection (FPAD) is becoming an increasingly challenging problem due to the continuous advancement of attack techniques, which generate `realistic-looking’ fake fingerprint presentations. Recently, laser speckle contrast imaging (LSCI) has been introduced as a new sensing modality for FPAD. LSCI has the interesting characteristic of capturing the blood flow under the skin surface. Toward studying the importance and effectiveness of LSCI for FPAD, we conduct a comprehensive study using different patch-based deep neural network architectures. Our studied architectures include 2D and 3D convolutional networks as well as a recurrent network using long short-term memory (LSTM) units. The study demonstrates that strong FPAD performance can be achieved using LSCI. We evaluate the different models over a new large dataset. The dataset consists of 3743 bona fide samples, collected from 335 unique subjects, and 218 presentation attack samples, including six different types of attacks. To examine the effect of changing the training and testing sets, we conduct a 3-fold cross validation evaluation. To examine the effect of the presence of an unseen attack, we apply a leave-one-attack out strategy. The FPAD classification results of the networks, which are separately optimized and tuned for the temporal and spatial patch-sizes, indicate that the best performance is achieved by LSTM. | |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02595v1 |
| https://arxiv.org/pdf/1906.02595v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-effectiveness-of-laser-speckle |
| Repo | |
| Framework | |
Generating Counterfactual and Contrastive Explanations using SHAP
| Title | Generating Counterfactual and Contrastive Explanations using SHAP |
| Authors | Shubham Rathi |
| Abstract | With the advent of GDPR, the domain of explainable AI and model interpretability has gained added impetus. Methods to extract and communicate visibility into decision-making models have become legal requirement. Two specific types of explanations, contrastive and counterfactual have been identified as suitable for human understanding. In this paper, we propose a model agnostic method and its systemic implementation to generate these explanations using shapely additive explanations (SHAP). We discuss a generative pipeline to create contrastive explanations and use it to further to generate counterfactual datapoints. This pipeline is tested and discussed on the IRIS, Wine Quality & Mobile Features dataset. Analysis of the results obtained follows. |
| Tasks | Decision Making |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09293v1 |
| https://arxiv.org/pdf/1906.09293v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-counterfactual-and-contrastive |
| Repo | |
| Framework | |
Interactive Concept Mining on Personal Data – Bootstrapping Semantic Services
| Title | Interactive Concept Mining on Personal Data – Bootstrapping Semantic Services |
| Authors | Markus Schröder, Christian Jilek, Andreas Dengel |
| Abstract | Semantic services (e.g. Semantic Desktops) are still afflicted by a cold start problem: in the beginning, the user’s personal information sphere, i.e. files, mails, bookmarks, etc., is not represented by the system. Information extraction tools used to kick-start the system typically create 1:1 representations of the different information items. Higher level concepts, for example found in file names, mail subjects or in the content body of these items, are not extracted. Leaving these concepts out may lead to underperformance, having to many of them (e.g. by making every found term a concept) will clutter the arising knowledge graph with non-helpful relations. In this paper, we present an interactive concept mining approach proposing concept candidates gathered by exploiting given schemata of usual personal information management applications and analysing the personal information sphere using various metrics. To heed the subjective view of the user, a graphical user interface allows to easily rank and give feedback on proposed concept candidates, thus keeping only those actually considered relevant. A prototypical implementation demonstrates major steps of our approach. |
| Tasks | |
| Published | 2019-03-14 |
| URL | http://arxiv.org/abs/1903.05872v1 |
| http://arxiv.org/pdf/1903.05872v1.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-concept-mining-on-personal-data |
| Repo | |
| Framework | |
Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor
| Title | Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor |
| Authors | Malvina Nissim, Rik van Noord, Rob van der Goot |
| Abstract | Analogies such as “man is to king as woman is to X” are often used to illustrate the amazing power of word embeddings. Concurrently, they have also been used to expose how strongly human biases are encoded in vector spaces built on natural language, like “man is to computer programmer as woman is to homemaker”. Recent work has shown that analogies are in fact not such a diagnostic for bias, and other methods have been proven to be more apt to the task. However, beside the intrinsic problems with the analogy task as a bias detection tool, in this paper we show that a series of issues related to how analogies have been implemented and used might have yielded a distorted picture of bias in word embeddings. Human biases are present in word embeddings and need to be addressed. Analogies, though, are probably not the right tool to do so. Also, the way they have been most often used has exacerbated some possibly non-existing biases and perhaps hid others. Because they are still widely popular, and some of them have become classics within and outside the NLP community, we deem it important to provide a series of clarifications that should put well-known, and potentially new cases into the right perspective. |
| Tasks | Word Embeddings |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09866v2 |
| https://arxiv.org/pdf/1905.09866v2.pdf | |
| PWC | https://paperswithcode.com/paper/fair-is-better-than-sensationalman-is-to |
| Repo | |
| Framework | |
Understanding Player Engagement and In-Game Purchasing Behavior with Ensemble Learning
| Title | Understanding Player Engagement and In-Game Purchasing Behavior with Ensemble Learning |
| Authors | Anna Guitart, Ana Fernández del Río, África Periáñez |
| Abstract | As video games attract more and more players, the major challenge for game studios is to retain them. We present a deep behavioral analysis of churn (game abandonment) and what we called “purchase churn” (the transition from paying to non-paying user). A series of churning behavior profiles are identified, which allows a classification of churners in terms of whether they eventually return to the game (false churners)–or start purchasing again (false purchase churners)–and their subsequent behavior. The impact of excluding some or all of these churners from the training sample is then explored in several churn and purchase churn prediction models. Our results suggest that discarding certain combinations of “zombies” (players whose activity is extremely sporadic) and false churners has a significant positive impact in all models considered. |
| Tasks | |
| Published | 2019-07-09 |
| URL | https://arxiv.org/abs/1907.03947v1 |
| https://arxiv.org/pdf/1907.03947v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-player-engagement-and-in-game |
| Repo | |
| Framework | |
Exploiting Relevance for Online Decision-Making in High-Dimensions
| Title | Exploiting Relevance for Online Decision-Making in High-Dimensions |
| Authors | Eralp Turgay, Cem Bulucu, Cem Tekin |
| Abstract | Many sequential decision-making tasks require choosing at each decision step the right action out of the vast set of possibilities by extracting actionable intelligence from high-dimensional data streams. Most of the times, the high-dimensionality of actions and data makes learning of the optimal actions by traditional learning methods impracticable. In this work, we investigate how to discover and leverage the low-dimensional structure in actions and data to enable fast learning. As our learning model, we consider a structured contextual multi-armed bandit (CMAB) with high-dimensional arm (action) and context (data) sets, where the rewards depend only on a few relevant dimensions of the joint context-arm set. We depart from the prior work by assuming a high-dimensional and uncountable arm set, and allow relevant context dimensions to vary for each arm. We propose a new online learning algorithm called CMAB with Relevance Learning (CMAB-RL) and prove that its time-averaged regret asymptotically goes to zero. CMAB-RL enjoys a substantially improved regret bound compared to classical CMAB algorithms whose regrets depend on the dimensions $d_x$ and $d_a$ of the context and arm sets. Importantly, we show that if the learner knows upper bounds $\overline{d}_x$ and $\overline{d}_a$ on the number of relevant context and arm dimensions, then CMAB-RL achieves $\tilde{O}(T^{1 - 1 /(2 + 2\overline{d}_x + \overline{d}_a)})$ regret. Finally, we illustrate how CMAB algorithms can be used for optimal personalized blood glucose control in type 1 diabetes mellitus patients, and show that CMAB-RL outperforms other contextual MAB algorithms in this task, where the contexts represent multimodal physiological data streams obtained from sensor readings and the arms represent bolus insulin doses that are appropriate for injection. |
| Tasks | Decision Making |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00783v1 |
| https://arxiv.org/pdf/1907.00783v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-relevance-for-online-decision |
| Repo | |
| Framework | |
ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection
| Title | ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection |
| Authors | Saurabh Jha, Subho S. Banerjee, Timothy Tsai, Siva K. S. Hari, Michael B. Sullivan, Zbigniew T. Kalbarczyk, Stephen W. Keckler, Ravishankar K. Iyer |
| Abstract | The safety and resilience of fully autonomous vehicles (AVs) are of significant concern, as exemplified by several headline-making accidents. While AV development today involves verification, validation, and testing, end-to-end assessment of AV systems under accidental faults in realistic driving scenarios has been largely unexplored. This paper presents DriveFI, a machine learning-based fault injection engine, which can mine situations and faults that maximally impact AV safety, as demonstrated on two industry-grade AV technology stacks (from NVIDIA and Baidu). For example, DriveFI found 561 safety-critical faults in less than 4 hours. In comparison, random injection experiments executed over several weeks could not find any safety-critical faults |
| Tasks | Autonomous Vehicles |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.01051v1 |
| https://arxiv.org/pdf/1907.01051v1.pdf | |
| PWC | https://paperswithcode.com/paper/ml-based-fault-injection-for-autonomous |
| Repo | |
| Framework | |
