January 29, 2020

3295 words 16 mins read

Paper Group ANR 635

MANGA: Method Agnostic Neural-policy Generalization and Adaptation. Detecting and Correcting Adversarial Images Using Image Processing Operations. A Neural Spiking Approach Compared to Deep Feedforward Networks on Stepwise Pixel Erasement. Personalized Bundle List Recommendation. The Skipping Behavior of Users of Music Streaming Services and its Re …

MANGA: Method Agnostic Neural-policy Generalization and Adaptation


Title	MANGA: Method Agnostic Neural-policy Generalization and Adaptation
Authors	Homanga Bharadhwaj, Shoichiro Yamaguchi, Shin-ichi Maeda
Abstract	In this paper we target the problem of transferring policies across multiple environments with different dynamics parameters and motor noise variations, by introducing a framework that decouples the processes of policy learning and system identification. Efficiently transferring learned policies to an unknown environment with changes in dynamics configurations in the presence of motor noise is very important for operating robots in the real world, and our work is a novel attempt in that direction. We introduce MANGA: Method Agnostic Neural-policy Generalization and Adaptation, that trains dynamics conditioned policies and efficiently learns to estimate the dynamics parameters of the environment given off-policy state-transition rollouts in the environment. Our scheme is agnostic to the type of training method used - both reinforcement learning (RL) and imitation learning (IL) strategies can be used. We demonstrate the effectiveness of our approach by experimenting with four different MuJoCo agents and comparing against previously proposed transfer baselines.
Tasks	Imitation Learning
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08444v1
PDF	https://arxiv.org/pdf/1911.08444v1.pdf
PWC	https://paperswithcode.com/paper/manga-method-agnostic-neural-policy
Repo
Framework

Detecting and Correcting Adversarial Images Using Image Processing Operations


Title	Detecting and Correcting Adversarial Images Using Image Processing Operations
Authors	Huy H. Nguyen, Minoru Kuribayashi, Junichi Yamagishi, Isao Echizen
Abstract	Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry. However, DNNs are vulnerable to adversarial machine learning attacks, in which noise is added to the input to change the network output. We have devised an image-processing-based method to detect adversarial images based on our observation that adversarial noise is reduced after applying these operations while the normal images almost remain unaffected. In addition to detection, this method can be used to restore the adversarial images’ original labels, which is crucial to restoring the normal functionalities of DNN-based systems. Testing using an adversarial machine learning database we created for generating several types of attack using images from the ImageNet Large Scale Visual Recognition Challenge database demonstrated the efficiency of our proposed method for both detection and correction.
Tasks	Object Recognition
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05391v2
PDF	https://arxiv.org/pdf/1912.05391v2.pdf
PWC	https://paperswithcode.com/paper/detecting-and-correcting-adversarial-images
Repo
Framework

A Neural Spiking Approach Compared to Deep Feedforward Networks on Stepwise Pixel Erasement


Title	A Neural Spiking Approach Compared to Deep Feedforward Networks on Stepwise Pixel Erasement
Authors	René Larisch, Michael Teichmann, Fred H. Hamker
Abstract	In real world scenarios, objects are often partially occluded. This requires a robustness for object recognition against these perturbations. Convolutional networks have shown good performances in classification tasks. The learned convolutional filters seem similar to receptive fields of simple cells found in the primary visual cortex. Alternatively, spiking neural networks are more biological plausible. We developed a two layer spiking network, trained on natural scenes with a biologically plausible learning rule. It is compared to two deep convolutional neural networks using a classification task of stepwise pixel erasement on MNIST. In comparison to these networks the spiking approach achieves good accuracy and robustness.
Tasks	Object Recognition
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03201v1
PDF	https://arxiv.org/pdf/1912.03201v1.pdf
PWC	https://paperswithcode.com/paper/a-neural-spiking-approach-compared-to-deep
Repo
Framework

Personalized Bundle List Recommendation


Title	Personalized Bundle List Recommendation
Authors	Jinze Bai, Chang Zhou, Junshuai Song, Xiaoru Qu, Weiting An, Zhao Li, Jun Gao
Abstract	Product bundling, offering a combination of items to customers, is one of the marketing strategies commonly used in online e-commerce and offline retailers. A high-quality bundle generalizes frequent items of interest, and diversity across bundles boosts the user-experience and eventually increases transaction volume. In this paper, we formalize the personalized bundle list recommendation as a structured prediction problem and propose a bundle generation network (BGN), which decomposes the problem into quality/diversity parts by the determinantal point processes (DPPs). BGN uses a typical encoder-decoder framework with a proposed feature-aware softmax to alleviate the inadequate representation of traditional softmax, and integrates the masked beam search and DPP selection to produce high-quality and diversified bundle list with an appropriate bundle size. We conduct extensive experiments on three public datasets and one industrial dataset, including two generated from co-purchase records and the other two extracted from real-world online bundle services. BGN significantly outperforms the state-of-the-art methods in terms of quality, diversity and response time over all datasets. In particular, BGN improves the precision of the best competitors by 16% on average while maintaining the highest diversity on four datasets, and yields a 3.85x improvement of response time over the best competitors in the bundle list recommendation problem.
Tasks	Point Processes, Structured Prediction
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01933v1
PDF	http://arxiv.org/pdf/1904.01933v1.pdf
PWC	https://paperswithcode.com/paper/personalized-bundle-list-recommendation
Repo
Framework

The Skipping Behavior of Users of Music Streaming Services and its Relation to Musical Structure


Title	The Skipping Behavior of Users of Music Streaming Services and its Relation to Musical Structure
Authors	Nicola Montecchio, Pierre Roy, François Pachet
Abstract	The behavior of users of music streaming services is investigated from the point of view of the temporal dimension of individual songs; specifically, the main object of the analysis is the point in time within a song at which users stop listening and start streaming another song (“skip”). The main contribution of this study is the ascertainment of a correlation between the distribution in time of skipping events and the musical structure of songs. It is also shown that such distribution is not only specific to the individual songs, but also independent of the cohort of users and, under stationary conditions, date of observation. Finally, user behavioral data is used to train a predictor of the musical structure of a song solely from its acoustic content; it is shown that the use of such data, available in large quantities to music streaming services, yields significant improvements in accuracy over the customary fashion of training this class of algorithms, in which only smaller amounts of hand-labeled data are available.
Tasks
Published	2019-03-12
URL	http://arxiv.org/abs/1903.06008v1
PDF	http://arxiv.org/pdf/1903.06008v1.pdf
PWC	https://paperswithcode.com/paper/the-skipping-behavior-of-users-of-music
Repo
Framework

Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings


Title	Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
Authors	Matt Le, Stephen Roller, Laetitia Papaxanthos, Douwe Kiela, Maximilian Nickel
Abstract	We consider the task of inferring is-a relationships from large text corpora. For this purpose, we propose a new method combining hyperbolic embeddings and Hearst patterns. This approach allows us to set appropriate constraints for inferring concept hierarchies from distributional contexts while also being able to predict missing is-a relationships and to correct wrong extractions. Moreover – and in contrast with other methods – the hierarchical nature of hyperbolic space allows us to learn highly efficient representations and to improve the taxonomic consistency of the inferred hierarchies. Experimentally, we show that our approach achieves state-of-the-art performance on several commonly-used benchmarks.
Tasks
Published	2019-02-03
URL	http://arxiv.org/abs/1902.00913v1
PDF	http://arxiv.org/pdf/1902.00913v1.pdf
PWC	https://paperswithcode.com/paper/inferring-concept-hierarchies-from-text
Repo
Framework

Microsoft Research Asia’s Systems for WMT19


Title	Microsoft Research Asia’s Systems for WMT19
Authors	Yingce Xia, Xu Tan, Fei Tian, Fei Gao, Weicong Chen, Yang Fan, Linyuan Gong, Yichong Leng, Renqian Luo, Yiren Wang, Lijun Wu, Jinhua Zhu, Tao Qin, Tie-Yan Liu
Abstract	We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place for the other three. Our basic systems are built on Transformer, back translation and knowledge distillation. We integrate several of our rececent techniques to enhance the baseline systems: multi-agent dual learning (MADL), masked sequence-to-sequence pre-training (MASS), neural architecture optimization (NAO), and soft contextual data augmentation (SCA).
Tasks	Data Augmentation
Published	2019-11-07
URL	https://arxiv.org/abs/1911.06191v1
PDF	https://arxiv.org/pdf/1911.06191v1.pdf
PWC	https://paperswithcode.com/paper/microsoft-research-asias-systems-for-wmt19-1
Repo
Framework

Active Learning for One-Class Classification Using Two One-Class Classifiers


Title	Active Learning for One-Class Classification Using Two One-Class Classifiers
Authors	Patrick Schlachter, Bin Yang
Abstract	This paper introduces a novel, generic active learning method for one-class classification. Active learning methods play an important role to reduce the efforts of manual labeling in the field of machine learning. Although many active learning approaches have been proposed during the last years, most of them are restricted on binary or multi-class problems. One-class classifiers use samples from only one class, the so-called target class, during training and hence require special active learning strategies. The few strategies proposed for one-class classification either suffer from their limitation on specific one-class classifiers or their performance depends on particular assumptions about datasets like imbalance. Our proposed method bases on using two one-class classifiers, one for the desired target class and one for the so-called outlier class. It allows to invent new query strategies, to use binary query strategies and to define simple stopping criteria. Based on the new method, two query strategies are proposed. The provided experiments compare the proposed approach with known strategies on various datasets and show improved results in almost all situations.
Tasks	Active Learning
Published	2019-01-10
URL	http://arxiv.org/abs/1901.03124v1
PDF	http://arxiv.org/pdf/1901.03124v1.pdf
PWC	https://paperswithcode.com/paper/active-learning-for-one-class-classification
Repo
Framework

Machine Learning Solutions for High Energy Physics: Applications to Electromagnetic Shower Generation, Flavor Tagging, and the Search for di-Higgs Production


Title	Machine Learning Solutions for High Energy Physics: Applications to Electromagnetic Shower Generation, Flavor Tagging, and the Search for di-Higgs Production
Authors	Michela Paganini
Abstract	This thesis demonstrate the efficacy of designing and developing machine learning (ML) algorithms to selected use cases that encompass many of the outstanding challenges in the field of experimental high energy physics. Although simple implementations of neural networks and boosted decision trees have been used in high energy physics for a long time, the field of ML has quickly evolved by devising more complex, fast and stable implementations of learning algorithms. The complexity and power of state-of-the-art deep learning far exceeds those of the learning algorithms implemented in the CERN-developed \texttt{ROOT} library. All aspects of experimental high energy physics have been and will continue being revolutionized by the software- and hardware-based technological advances spearheaded by both academic and industrial research in other technical disciplines, and the emergent trend of increased interdisciplinarity will soon reframe many scientific domains. This thesis exemplifies this spirit of versatility and multidisciplinarity by bridging the gap between ML and particle physics, and exploring original lines of work to modernize the reconstruction, particle identification, simulation, and analysis workflows. This contribution documents a collection of novel approaches to augment traditional domain-specific methods with modern, automated techniques based on industry-standard, open-source libraries. Specifically, it contributes to setting the state-of-the-art for impact parameter-based flavor tagging and di-Higgs searches in the $\gamma \gamma b\bar{b} $ channel with the ATLAS detector at the LHC, it introduces and lays the foundations for the use of generative adversarial networks for the simulation of particle showers in calorimeters. These results substantiate the notion of ML powering particle physics in the upcoming years and establish baselines for future applications.
Tasks
Published	2019-03-12
URL	http://arxiv.org/abs/1903.05082v1
PDF	http://arxiv.org/pdf/1903.05082v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-solutions-for-high-energy
Repo
Framework

Video to Events: Recycling Video Datasets for Event Cameras


Title	Video to Events: Recycling Video Datasets for Event Cameras
Authors	Daniel Gehrig, Mathias Gehrig, Javier Hidalgo-Carrió, Davide Scaramuzza
Abstract	Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous “events” instead of intensity frames. They offer significant advantages with respect to conventional cameras: high dynamic range (HDR), high temporal resolution, and no motion blur. Recently, novel learning approaches operating on event data have achieved impressive results. Yet, these methods require a large amount of event data for training, which is hardly available due the novelty of event sensors in computer vision research. In this paper, we present a method that addresses these needs by converting any existing video dataset recorded with conventional cameras to synthetic event data. This unlocks the use of a virtually unlimited number of existing video datasets for training networks designed for real event data. We evaluate our method on two relevant vision tasks, i.e., object recognition and semantic segmentation, and show that models trained on synthetic events have several benefits: (i) they generalize well to real event data, even in scenarios where standard-camera images are blurry or overexposed, by inheriting the outstanding properties of event cameras; (ii) they can be used for fine-tuning on real data to improve over state-of-the-art for both classification and semantic segmentation.
Tasks	Object Recognition, Semantic Segmentation
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03095v2
PDF	https://arxiv.org/pdf/1912.03095v2.pdf
PWC	https://paperswithcode.com/paper/video-to-events-bringing-modern-computer
Repo
Framework

Is Word Segmentation Necessary for Deep Learning of Chinese Representations?


Title	Is Word Segmentation Necessary for Deep Learning of Chinese Representations?
Authors	Xiaoya Li, Yuxian Meng, Xiaofei Sun, Qinghong Han, Arianna Yuan, Jiwei Li
Abstract	Segmenting a chunk of text into words is usually the first step of processing Chinese text, but its necessity has rarely been explored. In this paper, we ask the fundamental question of whether Chinese word segmentation (CWS) is necessary for deep learning-based Chinese Natural Language Processing. We benchmark neural word-based models which rely on word segmentation against neural char-based models which do not involve word segmentation in four end-to-end NLP benchmark tasks: language modeling, machine translation, sentence matching/paraphrase and text classification. Through direct comparisons between these two types of models, we find that char-based models consistently outperform word-based models. Based on these observations, we conduct comprehensive experiments to study why word-based models underperform char-based models in these deep learning-based NLP tasks. We show that it is because word-based models are more vulnerable to data sparsity and the presence of out-of-vocabulary (OOV) words, and thus more prone to overfitting. We hope this paper could encourage researchers in the community to rethink the necessity of word segmentation in deep learning-based Chinese Natural Language Processing. \footnote{Yuxian Meng and Xiaoya Li contributed equally to this paper.}
Tasks	Chinese Word Segmentation, Language Modelling, Machine Translation, Text Classification
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05526v2
PDF	https://arxiv.org/pdf/1905.05526v2.pdf
PWC	https://paperswithcode.com/paper/is-word-segmentation-necessary-for-deep
Repo
Framework

A proof of convergence of multi-class logistic regression network


Title	A proof of convergence of multi-class logistic regression network
Authors	Marek Rychlik
Abstract	This paper revisits the special type of a neural network known under two names. In the statistics and machine learning community it is known as a multi-class logistic regression neural network. In the neural network community, it is simply the soft-max layer. The importance is underscored by its role in deep learning: as the last layer, whose autput is actually the classification of the input patterns, such as images. Our exposition focuses on mathematically rigorous derivation of the key equation expressing the gradient. The fringe benefit of our approach is a fully vectorized expression, which is a basis of an efficient implementation. The second result of this paper is the positivity of the second derivative of the cross-entropy loss function as function of the weights. This result proves that optimization methods based on convexity may be used to train this network. As a corollary, we demonstrate that no $L^2$-regularizer is needed to guarantee convergence of gradient descent.
Tasks
Published	2019-03-29
URL	http://arxiv.org/abs/1903.12600v3
PDF	http://arxiv.org/pdf/1903.12600v3.pdf
PWC	https://paperswithcode.com/paper/a-proof-of-convergence-of-multi-class
Repo
Framework

Continual egocentric object recognition


Title	Continual egocentric object recognition
Authors	Luca Erculiani, Fausto Giunchiglia, Andrea Passerini
Abstract	We present a framework capable of tackilng the problem of continual object recognition in a setting which resembles that under whichhumans see and learn. This setting has a set of unique characteristics:it assumes an egocentric point-of-view bound to the needs of a singleperson, which implies a relatively low diversity of data and a coldstart with no data; it requires to operate in an open world, where newobjects can be encounteredat any time; supervision is scarce and hasto be solicited to the user, and completelyunsupervised recognitionof new objects should be possible. Note that this setting differs fromthe one addressed in the open world recognition literature, where supervised feedback is always requested to be able to incorporate newobjects. We propose a first solution to this problem in the form ofa memory-based incremental framework that is capable of storinginformation of each and any object it encounters, while using the supervision of the user to learn to discriminate between known and unknown objects. Our approach is based on four main features: the useof time and space persistence (i.e., the appearance of objects changesrelatively slowly), the use of similarity as the main driving principlefor object recognition and novelty detection, the progressive introduction of new objects in a developmental fashion and the selectiveelicitation of user feedback in an online active learning fashion. Experimental results show the feasibility of open world, generic objectrecognition, the ability to recognize, memorize and re-identify newobjects even in complete absence of user supervision, and the utilityof persistence and incrementality in boosting performance.
Tasks	Active Learning, Object Recognition
Published	2019-12-06
URL	https://arxiv.org/abs/1912.05029v2
PDF	https://arxiv.org/pdf/1912.05029v2.pdf
PWC	https://paperswithcode.com/paper/continual-egocentric-object-recognition
Repo
Framework

Increasing Generality in Machine Learning through Procedural Content Generation


Title	Increasing Generality in Machine Learning through Procedural Content Generation
Authors	Sebastian Risi, Julian Togelius
Abstract	Procedural Content Generation (PCG) refers to the practice, in videogames and other games, of generating content such as levels, quests, or characters algorithmically. Motivated by the need to make games replayable, as well as to reduce authoring burden, limit storage space requirements, and enable particular aesthetics, a large number of PCG methods have been devised by game developers. Additionally, researchers have explored adapting methods from machine learning, optimization, and constraint solving to PCG problems. Games have been widely used in AI research since the inception of the field, and in recent years have been used to develop and benchmark new machine learning algorithms. Through this practice, it has become more apparent that these algorithms are susceptible to overfitting. Often, an algorithm will not learn a general policy, but instead a policy that will only work for a particular version of a particular task with particular initial parameters. In response, researchers have begun exploring randomization of problem parameters to counteract such overfitting and to allow trained policies to more easily transfer from one environment to another, such as from a simulated robot to a robot in the real world. Here we review the large amount of existing work on PCG, which we believe has an important role to play in increasing the generality of machine learning methods. The main goal here is to present RL/AI with new tools from the PCG toolbox, and its secondary goal is to explain to game developers and researchers a way in which their work is relevant to AI research.
Tasks
Published	2019-11-29
URL	https://arxiv.org/abs/1911.13071v2
PDF	https://arxiv.org/pdf/1911.13071v2.pdf
PWC	https://paperswithcode.com/paper/procedural-content-generation-from
Repo
Framework

Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents


Title	Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents
Authors	Nusrah Hussain, Engin Erzin, T. Metin Sezgin, Yucel Yemez
Abstract	The ability to generate appropriate verbal and non-verbal backchannels by an agent during human-robot interaction greatly enhances the interaction experience. Backchannels are particularly important in applications like tutoring and counseling, which require constant attention and engagement of the user. We present here a method for training a robot for backchannel generation during a human-robot interaction within the reinforcement learning (RL) framework, with the goal of maintaining high engagement level. Since online learning by interaction with a human is highly time-consuming and impractical, we take advantage of the recorded human-to-human dataset and approach our problem as a batch reinforcement learning problem. The dataset is utilized as a batch data acquired by some behavior policy. We perform experiments with laughs as a backchannel and train an agent with value-based techniques. In particular, we demonstrate the effectiveness of recurrent layers in the approximate value function for this problem, that boosts the performance in partially observable environments. With off-policy policy evaluation, it is shown that the RL agents are expected to produce more engagement than an agent trained from imitation learning.
Tasks	Imitation Learning, Q-Learning
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02037v1
PDF	https://arxiv.org/pdf/1908.02037v1.pdf
PWC	https://paperswithcode.com/paper/batch-recurrent-q-learning-for-backchannel
Repo
Framework