January 28, 2020

3200 words 16 mins read

Paper Group ANR 832

Deep learning based pulse shape discrimination for germanium detectors. Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems. Strategic Prediction with Latent Aggregative Games. End-to-End Adversarial Learning for Intrusion Detection in Computer Networks. Synthesizing Action Sequences for Modifying Model Decisions. An En …

Deep learning based pulse shape discrimination for germanium detectors


Title	Deep learning based pulse shape discrimination for germanium detectors
Authors	P. Holl, L. Hauertmann, B. Majorovits, O. Schulz, M. Schuster, A. J. Zsigmond
Abstract	Experiments searching for rare processes like neutrinoless double beta decay heavily rely on the identification of background events to reduce their background level and increase their sensitivity. We present a novel machine learning based method to recognize one of the most abundant classes of background events in these experiments. By combining a neural network for feature extraction with a smaller classification network, our method can be trained with only a small number of labeled events. To validate our method, we use signals from a broad-energy germanium detector irradiated with a $^{228}$Th gamma source. We find that it matches the performance of state-of-the-art algorithms commonly used for this detector type. However, it requires less tuning and calibration and shows potential to identify certain types of background events missed by other methods.
Tasks	Calibration
Published	2019-03-04
URL	https://arxiv.org/abs/1903.01462v2
PDF	https://arxiv.org/pdf/1903.01462v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-pulse-shape
Repo
Framework

Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems


Title	Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems
Authors	Mansour Saffar Mehrjardi, Amine Trabelsi, Osmar R. Zaiane
Abstract	Self-attentional models are a new paradigm for sequence modelling tasks which differ from common sequence modelling methods, such as recurrence-based and convolution-based sequence learning, in the way that their architecture is only based on the attention mechanism. Self-attentional models have been used in the creation of the state-of-the-art models in many NLP tasks such as neural machine translation, but their usage has not been explored for the task of training end-to-end task-oriented dialogue generation systems yet. In this study, we apply these models on the three different datasets for training task-oriented chatbots. Our finding shows that self-attentional models can be exploited to create end-to-end task-oriented chatbots which not only achieve higher evaluation scores compared to recurrence-based models, but also do so more efficiently.
Tasks	Dialogue Generation, Machine Translation
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05246v1
PDF	https://arxiv.org/pdf/1909.05246v1.pdf
PWC	https://paperswithcode.com/paper/self-attentional-models-application-in-task
Repo
Framework

Strategic Prediction with Latent Aggregative Games


Title	Strategic Prediction with Latent Aggregative Games
Authors	Vikas K. Garg, Tommi Jaakkola
Abstract	We introduce a new class of context dependent, incomplete information games to serve as structured prediction models for settings with significant strategic interactions. Our games map the input context to outcomes by first condensing the input into private player types that specify the utilities, weighted interactions, as well as the initial strategies for the players. The game is played over multiple rounds where players respond to weighted aggregates of their neighbors’ strategies. The predicted output from the model is a mixed strategy profile (a near-Nash equilibrium) and each observation is thought of as a sample from this strategy profile. We introduce two new aggregator paradigms with provably convergent game dynamics, and characterize the conditions under which our games are identifiable from data. Our games can be parameterized in a transferable manner so that the sets of players can change from one game to another. We demonstrate empirically that our games as models can recover meaningful strategic interactions from real voting data.
Tasks	Structured Prediction
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12169v1
PDF	https://arxiv.org/pdf/1905.12169v1.pdf
PWC	https://paperswithcode.com/paper/strategic-prediction-with-latent-aggregative
Repo
Framework

End-to-End Adversarial Learning for Intrusion Detection in Computer Networks


Title	End-to-End Adversarial Learning for Intrusion Detection in Computer Networks
Authors	Bahram Mohammadi, Mohammad Sabokrou
Abstract	This paper presents a simple yet efficient method for an anomaly-based Intrusion Detection System (IDS). In reality, IDSs can be defined as a one-class classification system, where the normal traffic is the target class. The high diversity of network attacks in addition to the need for generalization, motivate us to propose a semi-supervised method. Inspired by the successes of Generative Adversarial Networks (GANs) for training deep models in semi-unsupervised setting, we have proposed an end-to-end deep architecture for IDS. The proposed architecture is composed of two deep networks, each of which trained by competing with each other to understand the underlying concept of the normal traffic class. The key idea of this paper is to compensate the lack of anomalous traffic by approximately obtain them from normal flows. In this case, our method is not biased towards the available intrusions in the training set leading to more accurate detection. The proposed method has been evaluated on NSL-KDD dataset. The results confirm that our method outperforms the other state-of-the-art approaches.
Tasks	Intrusion Detection
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11577v1
PDF	http://arxiv.org/pdf/1904.11577v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-adversarial-learning-for-intrusion
Repo
Framework

Synthesizing Action Sequences for Modifying Model Decisions


Title	Synthesizing Action Sequences for Modifying Model Decisions
Authors	Goutham Ramakrishnan, Yun Chan Lee, Aws Albarghouthi
Abstract	When a model makes a consequential decision, e.g., denying someone a loan, it needs to additionally generate actionable, realistic feedback on what the person can do to favorably change the decision. We cast this problem through the lens of program synthesis, in which our goal is to synthesize an optimal (realistically cheapest or simplest) sequence of actions that if a person executes successfully can change their classification. We present a novel and general approach that combines search-based program synthesis and test-time adversarial attacks to construct action sequences over a domain-specific set of actions. We demonstrate the effectiveness of our approach on a number of deep neural networks.
Tasks	Program Synthesis
Published	2019-09-30
URL	https://arxiv.org/abs/1910.00057v3
PDF	https://arxiv.org/pdf/1910.00057v3.pdf
PWC	https://paperswithcode.com/paper/synthesizing-action-sequences-for-modifying
Repo
Framework

An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classification


Title	An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classification
Authors	Yue Ma, Zengfeng Zeng, Dawei Zhu, Xuan Li, Yiying Yang, Xiaoyuan Yao, Kaijie Zhou, Jianping Shen
Abstract	This paper describes our approach in DSTC 8 Track 4: Schema-Guided Dialogue State Tracking. The goal of this task is to predict the intents and slots in each user turn to complete the dialogue state tracking (DST) based on the information provided by the task’s schema. Different from traditional stage-wise DST, we propose an end-to-end DST system to avoid error accumulation between the dialogue turns. The DST system consists of a machine reading comprehension (MRC) model for non-categorical slots and a Wide & Deep model for categorical slots. As far as we know, this is the first time that MRC and Wide & Deep model are applied to DST problem in a fully end-to-end way. Experimental results show that our framework achieves an excellent performance on the test dataset including 50% zero-shot services with a joint goal accuracy of 0.8652 and a slot tagging F1-Score of 0.9835.
Tasks	Dialogue State Tracking, Machine Reading Comprehension, Reading Comprehension
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09297v2
PDF	https://arxiv.org/pdf/1912.09297v2.pdf
PWC	https://paperswithcode.com/paper/an-end-to-end-dialogue-state-tracking-system
Repo
Framework

CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension


Title	CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension
Authors	Xingyi Duan, Baoxin Wang, Ziyue Wang, Wentao Ma, Yiming Cui, Dayong Wu, Shijin Wang, Ting Liu, Tianxiang Huo, Zhen Hu, Heng Wang, Zhiyuan Liu
Abstract	We present a Chinese judicial reading comprehension (CJRC) dataset which contains approximately 10K documents and almost 50K questions with answers. The documents come from judgment documents and the questions are annotated by law experts. The CJRC dataset can help researchers extract elements by reading comprehension technology. Element extraction is an important task in the legal field. However, it is difficult to predefine the element types completely due to the diversity of document types and causes of action. By contrast, machine reading comprehension technology can quickly extract elements by answering various questions from the long document. We build two strong baseline models based on BERT and BiDAF. The experimental results show that there is enough space for improvement compared to human annotators.
Tasks	Machine Reading Comprehension, Reading Comprehension
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09156v1
PDF	https://arxiv.org/pdf/1912.09156v1.pdf
PWC	https://paperswithcode.com/paper/cjrc-a-reliable-human-annotated-benchmark
Repo
Framework

Hybrid Recommender Systems: A Systematic Literature Review


Title	Hybrid Recommender Systems: A Systematic Literature Review
Authors	Erion Çano, Maurizio Morisio
Abstract	Recommender systems are software tools used to generate and provide suggestions for items and other entities to the users by exploiting various strategies. Hybrid recommender systems combine two or more recommendation strategies in different ways to benefit from their complementary advantages. This systematic literature review presents the state of the art in hybrid recommender systems of the last decade. It is the first quantitative review work completely focused in hybrid recommenders. We address the most relevant problems considered and present the associated data mining and recommendation techniques used to overcome them. We also explore the hybridization classes each hybrid recommender belongs to, the application domains, the evaluation process and proposed future research directions. Based on our findings, most of the studies combine collaborative filtering with another technique often in a weighted way. Also cold-start and data sparsity are the two traditional and top problems being addressed in 23 and 22 studies each, while movies and movie datasets are still widely used by most of the authors. As most of the studies are evaluated by comparisons with similar methods using accuracy metrics, providing more credible and user oriented evaluations remains a typical challenge. Besides this, newer challenges were also identified such as responding to the variation of user context, evolving user tastes or providing cross-domain recommendations. Being a hot topic, hybrid recommenders represent a good basis with which to respond accordingly by exploring newer opportunities such as contextualizing recommendations, involving parallel hybrid algorithms, processing larger datasets, etc.
Tasks	Accuracy Metrics, Recommendation Systems
Published	2019-01-12
URL	http://arxiv.org/abs/1901.03888v1
PDF	http://arxiv.org/pdf/1901.03888v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-recommender-systems-a-systematic
Repo
Framework

Robust Reading Comprehension with Linguistic Constraints via Posterior Regularization


Title	Robust Reading Comprehension with Linguistic Constraints via Posterior Regularization
Authors	Mantong Zhou, Minlie Huang, Xiaoyan Zhu
Abstract	In spite of great advancements of machine reading comprehension (RC), existing RC models are still vulnerable and not robust to different types of adversarial examples. Neural models over-confidently predict wrong answers to semantic different adversarial examples, while over-sensitively predict wrong answers to semantic equivalent adversarial examples. Existing methods which improve the robustness of such neural models merely mitigate one of the two issues but ignore the other. In this paper, we address the over-confidence issue and the over-sensitivity issue existing in current RC models simultaneously with the help of external linguistic knowledge. We first incorporate external knowledge to impose different linguistic constraints (entity constraint, lexical constraint, and predicate constraint), and then regularize RC models through posterior regularization. Linguistic constraints induce more reasonable predictions for both semantic different and semantic equivalent adversarial examples, and posterior regularization provides an effective mechanism to incorporate these constraints. Our method can be applied to any existing neural RC models including state-of-the-art BERT models. Extensive experiments show that our method remarkably improves the robustness of base RC models, and is better to cope with these two issues simultaneously.
Tasks	Machine Reading Comprehension, Reading Comprehension
Published	2019-11-16
URL	https://arxiv.org/abs/1911.06948v1
PDF	https://arxiv.org/pdf/1911.06948v1.pdf
PWC	https://paperswithcode.com/paper/robust-reading-comprehension-with-linguistic
Repo
Framework

SASSE: Scalable and Adaptable 6-DOF Pose Estimation


Title	SASSE: Scalable and Adaptable 6-DOF Pose Estimation
Authors	Huu Le, Tuan Hoang, Qianggong Zhang, Thanh-Toan Do, Anders Eriksson, Michael Milford
Abstract	Visual localization has become a key enabling component of many place recognition and SLAM systems. Contemporary research has primarily focused on improving accuracy and precision-recall type metrics, with relatively little attention paid to a system’s absolute storage scaling characteristics, its flexibility to adapt to available computational resources, and its longevity with respect to easily incorporating newly learned or hand-crafted image descriptors. Most significantly, improvement in one of these aspects typically comes at the cost of others: for example, a snapshot-based system that achieves sub-linear storage cost typically provides no metric pose estimation, or, a highly accurate pose estimation technique is often ossified in adapting to recent advances in appearance-invariant features. In this paper, we present a novel 6-DOF localization system that for the first time simultaneously achieves all the three characteristics: significantly sub-linear storage growth, agnosticism to image descriptors, and customizability to available storage and computational resources. The key features of our method are developed based on a novel adaptation of multiple-label learning, together with effective dimensional reduction and learning techniques that enable simple and efficient optimization. We evaluate our system on several large benchmarking datasets and provide detailed comparisons to state-of-the-art systems. The proposed method demonstrates competitive accuracy with existing pose estimation methods while achieving better sub-linear storage scaling, significantly reduced absolute storage requirements, and faster training and deployment speeds.
Tasks	Pose Estimation, Visual Localization
Published	2019-02-05
URL	http://arxiv.org/abs/1902.01549v1
PDF	http://arxiv.org/pdf/1902.01549v1.pdf
PWC	https://paperswithcode.com/paper/sasse-scalable-and-adaptable-6-dof-pose
Repo
Framework

Improving Machine Reading Comprehension via Adversarial Training


Title	Improving Machine Reading Comprehension via Adversarial Training
Authors	Ziqing Yang, Yiming Cui, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu
Abstract	Adversarial training (AT) as a regularization method has proved its effectiveness in various tasks, such as image classification and text classification. Though there are successful applications of AT in many tasks of natural language processing (NLP), the mechanism behind it is still unclear. In this paper, we aim to apply AT on machine reading comprehension (MRC) and study its effects from multiple perspectives. We experiment with three different kinds of RC tasks: span-based RC, span-based RC with unanswerable questions and multi-choice RC. The experimental results show that the proposed method can improve the performance significantly and universally on SQuAD1.1, SQuAD2.0 and RACE. With virtual adversarial training (VAT), we explore the possibility of improving the RC models with semi-supervised learning and prove that examples from a different task are also beneficial. We also find that AT helps little in defending against artificial adversarial examples, but AT helps the model to learn better on examples that contain more low-frequency words.
Tasks	Image Classification, Machine Reading Comprehension, Reading Comprehension, Text Classification
Published	2019-11-09
URL	https://arxiv.org/abs/1911.03614v1
PDF	https://arxiv.org/pdf/1911.03614v1.pdf
PWC	https://paperswithcode.com/paper/improving-machine-reading-comprehension-via
Repo
Framework

Determining Multifunctional Genes and Diseases in Human Using Gene Ontology


Title	Determining Multifunctional Genes and Diseases in Human Using Gene Ontology
Authors	Hisham Al-Mubaid, Sasikanth Potu, M. Shenify
Abstract	The study of human genes and diseases is very rewarding and can lead to improvements in healthcare, disease diagnostics and drug discovery. In this paper, we further our previous study on gene disease relationship specifically with the multifunctional genes. We investigate the multifunctional gene disease relationship based on the published molecular function annotations of genes from the Gene Ontology which is the most comprehensive source on gene functions.
Tasks	Drug Discovery
Published	2019-01-11
URL	http://arxiv.org/abs/1901.04847v1
PDF	http://arxiv.org/pdf/1901.04847v1.pdf
PWC	https://paperswithcode.com/paper/determining-multifunctional-genes-and
Repo
Framework

A method on selecting reliable samples based on fuzziness in positive and unlabeled learning


Title	A method on selecting reliable samples based on fuzziness in positive and unlabeled learning
Authors	TingTing Li, WeiYa Fan, YunSong Luo
Abstract	Traditional semi-supervised learning uses only labeled instances to train a classifier and then this classifier is utilized to classify unlabeled instances, while sometimes there are only positive instances which are elements of the target concept are available in the labeled set. Our research in this paper the design of learning algorithms from positive and unlabeled instances only. Among all the semi-supervised positive and unlabeled learning methods, it is a fundamental step to extract useful information from unlabeled instances. In this paper, we design a novel framework to take advantage of valid information in unlabeled instances. In essence, this framework mainly includes that (1) selects reliable negative instances through the fuzziness of the instances; (2) chooses new positive instances based on the fuzziness of the instances to expand the initial positive set, and we named these new instances as reliable positive instances; (3) uses data editing technique to filter out noise points with high fuzziness. The effectiveness of the presented algorithm is verified by comparative experiments on UCI dataset.
Tasks
Published	2019-03-26
URL	http://arxiv.org/abs/1903.11064v1
PDF	http://arxiv.org/pdf/1903.11064v1.pdf
PWC	https://paperswithcode.com/paper/a-method-on-selecting-reliable-samples-based
Repo
Framework

Graph Convolutional Networks with EigenPooling


Title	Graph Convolutional Networks with EigenPooling
Authors	Yao Ma, Suhang Wang, Charu C. Aggarwal, Jiliang Tang
Abstract	Graph neural networks, which generalize deep neural network models to graph structured data, have attracted increasing attention in recent years. They usually learn node representations by transforming, propagating and aggregating node features and have been proven to improve the performance of many graph related tasks such as node classification and link prediction. To apply graph neural networks for the graph classification task, approaches to generate the \textit{graph representation} from node representations are demanded. A common way is to globally combine the node representations. However, rich structural information is overlooked. Thus a hierarchical pooling procedure is desired to preserve the graph structure during the graph representation learning. There are some recent works on hierarchically learning graph representation analogous to the pooling step in conventional convolutional neural (CNN) networks. However, the local structural information is still largely neglected during the pooling process. In this paper, we introduce a pooling operator $\pooling$ based on graph Fourier transform, which can utilize the node features and local structures during the pooling process. We then design pooling layers based on the pooling operator, which are further combined with traditional GCN convolutional layers to form a graph neural network framework $\m$ for graph classification. Theoretical analysis is provided to understand $\pooling$ from both local and global perspectives. Experimental results of the graph classification task on $6$ commonly used benchmarks demonstrate the effectiveness of the proposed framework.
Tasks	Graph Classification, Graph Representation Learning, Link Prediction, Node Classification, Representation Learning
Published	2019-04-30
URL	https://arxiv.org/abs/1904.13107v2
PDF	https://arxiv.org/pdf/1904.13107v2.pdf
PWC	https://paperswithcode.com/paper/graph-convolutional-networks-with
Repo
Framework

Donkey and Smuggler Optimization Algorithm: A Collaborative Working Approach to Path Finding


Title	Donkey and Smuggler Optimization Algorithm: A Collaborative Working Approach to Path Finding
Authors	Ahmed S. Shamsaldin, Tarik A. Rashid, Rawan A. Al-Rashid Agha, Nawzad K. Al-Salihi, Mokhtar Mohammadi
Abstract	Swarm Intelligence is a metaheuristic optimization approach that has become very predominant over the last few decades. These algorithms are inspired by animals’ physical behaviors and their evolutionary perceptions. The simplicity of these algorithms allows researchers to simulate different natural phenomena to solve various real-world problems. This paper suggests a novel algorithm called Donkey and Smuggler Optimization Algorithm (DSO). The DSO is inspired by the searching behavior of donkeys. The algorithm imitates transportation behavior such as searching and selecting routes for movement by donkeys in the actual world. Two modes are established for implementing the search behavior and route-selection in this algorithm. These are the Smuggler and Donkeys. In the Smuggler mode, all the possible paths are discovered and the shortest path is then found. In the Donkeys mode, several donkey behaviors are utilized such as Run, Face & Suicide, and Face & Support. Real world data and applications are used to test the algorithm. The experimental results consisted of two parts, firstly, we used the standard benchmark test functions to evaluate the performance of the algorithm in respect to the most popular and the state of the art algorithms. Secondly, the DSO is adapted and implemented on three real-world applications namely; traveling salesman problem, packet routing, and ambulance routing. The experimental results of DSO on these real-world problems are very promising. The results exhibit that the suggested DSO is appropriate to tackle other unfamiliar search spaces and complex problems.
Tasks
Published	2019-04-19
URL	http://arxiv.org/abs/1904.09352v1
PDF	http://arxiv.org/pdf/1904.09352v1.pdf
PWC	https://paperswithcode.com/paper/190409352
Repo
Framework