January 26, 2020

2841 words 14 mins read

Paper Group ANR 1493

Natural and Adversarial Error Detection using Invariance to Image Transformations. CoopNet: Cooperative Convolutional Neural Network for Low-Power MCUs. Bandit Principal Component Analysis. Knowledge representation and diagnostic inference using Bayesian networks in the medical discourse. Probabilistic Multimodal Modeling for Human-Robot Interactio …

Natural and Adversarial Error Detection using Invariance to Image Transformations


Title	Natural and Adversarial Error Detection using Invariance to Image Transformations
Authors	Yuval Bahat, Michal Irani, Gregory Shakhnarovich
Abstract	We propose an approach to distinguish between correct and incorrect image classifications. Our approach can detect misclassifications which either occur $\it{unintentionally}$ (“natural errors”), or due to $\it{intentional~adversarial~attacks}$ (“adversarial errors”), both in a single $\it{unified~framework}$. Our approach is based on the observation that correctly classified images tend to exhibit robust and consistent classifications under certain image transformations (e.g., horizontal flip, small image translation, etc.). In contrast, incorrectly classified images (whether due to adversarial errors or natural errors) tend to exhibit large variations in classification results under such transformations. Our approach does not require any modifications or retraining of the classifier, hence can be applied to any pre-trained classifier. We further use state of the art targeted adversarial attacks to demonstrate that even when the adversary has full knowledge of our method, the adversarial distortion needed for bypassing our detector is $\it{no~longer~imperceptible~to~the~human~eye}$. Our approach obtains state-of-the-art results compared to previous adversarial detection methods, surpassing them by a large margin.
Tasks
Published	2019-02-01
URL	http://arxiv.org/abs/1902.00236v1
PDF	http://arxiv.org/pdf/1902.00236v1.pdf
PWC	https://paperswithcode.com/paper/natural-and-adversarial-error-detection-using
Repo
Framework

CoopNet: Cooperative Convolutional Neural Network for Low-Power MCUs


Title	CoopNet: Cooperative Convolutional Neural Network for Low-Power MCUs
Authors	Luca Mocerino, Andrea Calimera
Abstract	Fixed-point quantization and binarization are two reduction methods adopted to deploy Convolutional Neural Networks (CNN) on end-nodes powered by low-power micro-controller units (MCUs). While most of the existing works use them as stand-alone optimizations, this work aims at demonstrating there is margin for a joint cooperation that leads to inferential engines with lower latency and higher accuracy. Called CoopNet, the proposed heterogeneous model is conceived, implemented and tested on off-the-shelf MCUs with small on-chip memory and few computational resources. Experimental results conducted on three different CNNs using as test-bench the low-power RISC core of the Cortex-M family by ARM validate the CoopNet proposal by showing substantial improvements w.r.t. designs where quantization and binarization are applied separately.
Tasks	Quantization
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08606v3
PDF	https://arxiv.org/pdf/1911.08606v3.pdf
PWC	https://paperswithcode.com/paper/coopnet-cooperative-convolutional-neural
Repo
Framework

Bandit Principal Component Analysis


Title	Bandit Principal Component Analysis
Authors	Wojciech Kotłowski, Gergely Neu
Abstract	We consider a partial-feedback variant of the well-studied online PCA problem where a learner attempts to predict a sequence of $d$-dimensional vectors in terms of a quadratic loss, while only having limited feedback about the environment’s choices. We focus on a natural notion of bandit feedback where the learner only observes the loss associated with its own prediction. Based on the classical observation that this decision-making problem can be lifted to the space of density matrices, we propose an algorithm that is shown to achieve a regret of $O(d^{3/2}\sqrt{T})$ after $T$ rounds in the worst case. We also prove data-dependent bounds that improve on the basic result when the loss matrices of the environment have bounded rank or the loss of the best action is bounded. One version of our algorithm runs in $O(d)$ time per trial which massively improves over every previously known online PCA method. We complement these results by a lower bound of $\Omega(d\sqrt{T})$.
Tasks	Decision Making
Published	2019-02-08
URL	http://arxiv.org/abs/1902.03035v1
PDF	http://arxiv.org/pdf/1902.03035v1.pdf
PWC	https://paperswithcode.com/paper/bandit-principal-component-analysis
Repo
Framework

Knowledge representation and diagnostic inference using Bayesian networks in the medical discourse


Title	Knowledge representation and diagnostic inference using Bayesian networks in the medical discourse
Authors	Sebastian Flügge, Sandra Zimmer, Uwe Petersohn
Abstract	For the diagnostic inference under uncertainty Bayesian networks are investigated. The method is based on an adequate uniform representation of the necessary knowledge. This includes both generic and experience-based specific knowledge, which is stored in a knowledge base. For knowledge processing, a combination of the problem-solving methods of concept-based and case-based reasoning is used. Concept-based reasoning is used for the diagnosis, therapy and medication recommendation and evaluation of generic knowledge. Exceptions in the form of specific patient cases are processed by case-based reasoning. In addition, the use of Bayesian networks allows to deal with uncertainty, fuzziness and incompleteness. Thus, the valid general concepts can be issued according to their probability. To this end, various inference mechanisms are introduced and subsequently evaluated within the context of a developed prototype. Tests are employed to assess the classification of diagnoses by the network.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08549v1
PDF	https://arxiv.org/pdf/1909.08549v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-representation-and-diagnostic
Repo
Framework

Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks


Title	Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks
Authors	Joseph Campbell, Simon Stepputtis, Heni Ben Amor
Abstract	Human-robot interaction benefits greatly from multimodal sensor inputs as they enable increased robustness and generalization accuracy. Despite this observation, few HRI methods are capable of efficiently performing inference for multimodal systems. In this work, we introduce a reformulation of Interaction Primitives which allows for learning from demonstration of interaction tasks, while also gracefully handling nonlinearities inherent to multimodal inference in such scenarios. We also empirically show that our method results in more accurate, more robust, and faster inference than standard Interaction Primitives and other common methods in challenging HRI scenarios.
Tasks
Published	2019-08-14
URL	https://arxiv.org/abs/1908.04955v1
PDF	https://arxiv.org/pdf/1908.04955v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-multimodal-modeling-for-human
Repo
Framework

Multiplayer Multi-armed Bandits for Optimal Assignment in Heterogeneous Networks


Title	Multiplayer Multi-armed Bandits for Optimal Assignment in Heterogeneous Networks
Authors	Harshvardhan Tibrewal, Sravan Patchala, Manjesh K. Hanawal, Sumit J. Darak
Abstract	We consider an ad hoc network where multiple users access the same set of channels. The channel characteristics are unknown and could be different for each user (heterogeneous). No controller is available to coordinate channel selections by the users, and if multiple users select the same channel, they collide and none of them receive any rate (or reward). For such a completely decentralized network we develop algorithms that aim to achieve optimal network throughput. Due to lack of any direct communication between the users, we allow each user to exchange information by transmitting in a specific pattern and sense such transmissions from others. However, such transmissions and sensing for information exchange do not add to network throughput. For the wideband sensing and narrowband sensing scenarios, we first develop explore-and-commit algorithms that converge to near-optimal allocation with high probability in a small number of rounds. Building on this, we develop an algorithm that gives logarithmic regret, even when the number of users changes with time. We validate our claims through extensive experiments and show that our algorithms perform significantly better than the state-of-the-art CSM-MAB, dE3 and dE3-TS algorithms.
Tasks	Multi-Armed Bandits
Published	2019-01-12
URL	https://arxiv.org/abs/1901.03868v4
PDF	https://arxiv.org/pdf/1901.03868v4.pdf
PWC	https://paperswithcode.com/paper/distributed-learning-and-optimal-assignment
Repo
Framework

Regression-Enhanced Random Forests


Title	Regression-Enhanced Random Forests
Authors	Haozhe Zhang, Dan Nettleton, Zhengyuan Zhu
Abstract	Random forest (RF) methodology is one of the most popular machine learning techniques for prediction problems. In this article, we discuss some cases where random forests may suffer and propose a novel generalized RF method, namely regression-enhanced random forests (RERFs), that can improve on RFs by borrowing the strength of penalized parametric regression. The algorithm for constructing RERFs and selecting its tuning parameters is described. Both simulation study and real data examples show that RERFs have better predictive performance than RFs in important situations often encountered in practice. Moreover, RERFs may incorporate known relationships between the response and the predictors, and may give reliable predictions in extrapolation problems where predictions are required at points out of the domain of the training dataset. Strategies analogous to those described here can be used to improve other machine learning methods via combination with penalized parametric regression techniques.
Tasks
Published	2019-04-23
URL	http://arxiv.org/abs/1904.10416v1
PDF	http://arxiv.org/pdf/1904.10416v1.pdf
PWC	https://paperswithcode.com/paper/regression-enhanced-random-forests
Repo
Framework

Active Learning of SVDD Hyperparameter Values


Title	Active Learning of SVDD Hyperparameter Values
Authors	Holger Trittenbach, Klemens Böhm, Ira Assent
Abstract	Support Vector Data Description is a popular method for outlier detection. However, its usefulness largely depends on selecting good hyperparameter values – a difficult problem that has received significant attention in literature. Existing methods to estimate hyperparameter values are purely heuristic, and the conditions under which they work well are unclear. In this article, we propose LAMA (Local Active Min-Max Alignment), the first principled approach to estimate SVDD hyperparameter values by active learning. The core idea bases on kernel alignment, which we adapt to active learning with small sample sizes. In contrast to many existing approaches, LAMA provides estimates for both SVDD hyperparameters. These estimates are evidence-based, i.e., rely on actual class labels, and come with a quality score. This eliminates the need for manual validation, an issue with current heuristics. LAMA outperforms state-of-the-art competitors in extensive experiments on real-world data. In several cases, LAMA even yields results close to the empirical upper bound.
Tasks	Active Learning, Outlier Detection
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01927v1
PDF	https://arxiv.org/pdf/1912.01927v1.pdf
PWC	https://paperswithcode.com/paper/active-learning-of-svdd-hyperparameter-values
Repo
Framework

Force-based Algorithm for Motion Planning of Large Agent Teams


Title	Force-based Algorithm for Motion Planning of Large Agent Teams
Authors	Samaneh Hosseini Semnani, Anton de Ruiter, Hugh Liu
Abstract	This paper presents a distributed, efficient, scalable and real-time motion planning algorithm for a large group of agents moving in 2 or 3-dimensional spaces. This algorithm enables autonomous agents to generate individual trajectories independently with only the relative position information of neighboring agents. Each agent applies a force-based control that contains two main terms: collision avoidance and navigational feedback. The first term keeps two agents separate with a certain distance, while the second term attracts each agent toward its goal location. Compared with existing collision-avoidance algorithms, the proposed force-based motion planning (FMP) algorithm is able to find collision-free motions with lower transition time, free from velocity state information of neighbouring agents. It leads to less computational overhead. The performance of proposed FMP is examined over several dense and complex 2D and 3D benchmark simulation scenarios, with results outperforming existing methods.
Tasks	Motion Planning
Published	2019-09-10
URL	https://arxiv.org/abs/1909.05415v1
PDF	https://arxiv.org/pdf/1909.05415v1.pdf
PWC	https://paperswithcode.com/paper/force-based-algorithm-for-motion-planning-of
Repo
Framework

General Fair Empirical Risk Minimization


Title	General Fair Empirical Risk Minimization
Authors	Luca Oneto, Michele Donini, Massimiliano Pontil
Abstract	We tackle the problem of algorithmic fairness, where the goal is to avoid the unfairly influence of sensitive information, in the general context of regression with possible continuous sensitive attributes. We extend the framework of fair empirical risk minimization to this general scenario, covering in this way the whole standard supervised learning setting. Our generalized fairness measure reduces to well known notions of fairness available in literature. We derive learning guarantees for our method, that imply in particular its statistical consistency, both in terms of the risk and the fairness measure. We then specialize our approach to kernel methods and propose a convex fair estimator in that setting. We test the estimator on a commonly used benchmark dataset (Communities and Crime) and on a new dataset collected at the University of Genova, containing the information of the academic career of five thousand students. The latter dataset provides a challenging real case scenario of unfair behaviour of standard regression methods that benefits from our methodology. The experimental results show that our estimator is effective at mitigating the trade-off between accuracy and fairness requirements.
Tasks
Published	2019-01-29
URL	https://arxiv.org/abs/1901.10080v3
PDF	https://arxiv.org/pdf/1901.10080v3.pdf
PWC	https://paperswithcode.com/paper/general-fair-empirical-risk-minimization
Repo
Framework

Detection of fraudulent users in P2P financial market


Title	Detection of fraudulent users in P2P financial market
Authors	Hao Wang
Abstract	Financial fraud detection is one of the core technological assets of Fintech companies. It saves tens of millions of money fro m Chinese Fintech companies since the bad loan rate is more than 10%. HC Financial Service Group is the 3rd largest company in the Chinese P2P financial market. In this paper we illustrate how we tackle the fraud detection problem at HC Financial. We utilize two powerful workhorses in the machine learning field - random forest and gradient boosting decision tree to detect fraudulent users . We demonstrate that by carefully select features and tune model parameters , we could effectively filter out fraudulent users in the P2P market.
Tasks	Fraud Detection
Published	2019-09-24
URL	https://arxiv.org/abs/1910.02010v1
PDF	https://arxiv.org/pdf/1910.02010v1.pdf
PWC	https://paperswithcode.com/paper/detection-of-fraudulent-users-in-p2p
Repo
Framework


Title	A decentralized trust-aware collaborative filtering recommender system based on weighted items for social tagging systems
Authors	Hossein Monshizadeh Naeen, Mehrdad Jalali
Abstract	Recommender systems are used with the purpose of suggesting contents and resources to the users in a social network. These systems use ranks or tags each user assign to different resources to predict or make suggestions to users. Lately, social tagging systems, in which users can insert new contents, tag, organize, share, and search for contents are becoming more popular. These systems have a lot of valuable information, but data growth is one of its biggest challenges and this has led to the need for recommender systems that will predict what each user may like or need. One approach to the design of these systems which uses social environment of users is known as collaborative filtering (CF). One of the problems in CF systems is trustworthy of users and their tags. In this work, we consider a trust metric (which is concluded from users tagging behavior) beside the similarities to give suggestions and examine its effect on results. On the other hand, a decentralized approach is introduced which calculates similarity and trust relationships between users in a distributed manner. This causes the capability of implementing the proposed approach among all types of users with respect to different types of items, which are accessed by unique id across heterogeneous networks and environments. Finally, we show that the proposed model for calculating similarities between users reduces the size of the user-item matrix and considering trust in collaborative systems can lead to a better performance in generating suggestions.
Tasks	Recommendation Systems
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05143v1
PDF	https://arxiv.org/pdf/1906.05143v1.pdf
PWC	https://paperswithcode.com/paper/a-decentralized-trust-aware-collaborative
Repo
Framework

An Open Source AutoML Benchmark


Title	An Open Source AutoML Benchmark
Authors	Pieter Gijsbers, Erin LeDell, Janek Thomas, Sébastien Poirier, Bernd Bischl, Joaquin Vanschoren
Abstract	In recent years, an active field of research has developed around automated machine learning (AutoML). Unfortunately, comparing different AutoML systems is hard and often done incorrectly. We introduce an open, ongoing, and extensible benchmark framework which follows best practices and avoids common mistakes. The framework is open-source, uses public datasets and has a website with up-to-date results. We use the framework to conduct a thorough comparison of 4 AutoML systems across 39 datasets and analyze the results.
Tasks	AutoML
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00909v1
PDF	https://arxiv.org/pdf/1907.00909v1.pdf
PWC	https://paperswithcode.com/paper/an-open-source-automl-benchmark
Repo
Framework

Metric Learning for Individual Fairness


Title	Metric Learning for Individual Fairness
Authors	Christina Ilvento
Abstract	There has been much discussion recently about how fairness should be measured or enforced in classification. Individual Fairness [Dwork, Hardt, Pitassi, Reingold, Zemel, 2012], which requires that similar individuals be treated similarly, is a highly appealing definition as it gives strong guarantees on treatment of individuals. Unfortunately, the need for a task-specific similarity metric has prevented its use in practice. In this work, we propose a solution to the problem of approximating a metric for Individual Fairness based on human judgments. Our model assumes that we have access to a human fairness arbiter, who can answer a limited set of queries concerning similarity of individuals for a particular task, is free of explicit biases and possesses sufficient domain knowledge to evaluate similarity. Our contributions include definitions for metric approximation relevant for Individual Fairness, constructions for approximations from a limited number of realistic queries to the arbiter on a sample of individuals, and learning procedures to construct hypotheses for metric approximations which generalize to unseen samples under certain assumptions of learnability of distance threshold functions.
Tasks	Metric Learning
Published	2019-06-01
URL	https://arxiv.org/abs/1906.00250v1
PDF	https://arxiv.org/pdf/1906.00250v1.pdf
PWC	https://paperswithcode.com/paper/190600250
Repo
Framework

A neurally plausible model learns successor representations in partially observable environments


Title	A neurally plausible model learns successor representations in partially observable environments
Authors	Eszter Vertes, Maneesh Sahani
Abstract	Animals need to devise strategies to maximize returns while interacting with their environment based on incoming noisy sensory observations. Task-relevant states, such as the agent’s location within an environment or the presence of a predator, are often not directly observable but must be inferred using available sensory information. Successor representations (SR) have been proposed as a middle-ground between model-based and model-free reinforcement learning strategies, allowing for fast value computation and rapid adaptation to changes in the reward function or goal locations. Indeed, recent studies suggest that features of neural responses are consistent with the SR framework. However, it is not clear how such representations might be learned and computed in partially observed, noisy environments. Here, we introduce a neurally plausible model using distributional successor features, which builds on the distributed distributional code for the representation and computation of uncertainty, and which allows for efficient value function computation in partially observed environments via the successor representation. We show that distributional successor features can support reinforcement learning in noisy environments in which direct learning of successful policies is infeasible.
Tasks
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09480v1
PDF	https://arxiv.org/pdf/1906.09480v1.pdf
PWC	https://paperswithcode.com/paper/a-neurally-plausible-model-learns-successor
Repo
Framework