January 31, 2020

2945 words 14 mins read

Paper Group ANR 118

A Statistical Defense Approach for Detecting Adversarial Examples. Concise and Effective Network for 3D Human Modeling from Orthogonal Silhouettes. Understanding the Radical Mind: Identifying Signals to Detect Extremist Content on Twitter. HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion. Momentum in Reinforcement Learning. …

A Statistical Defense Approach for Detecting Adversarial Examples


Title	A Statistical Defense Approach for Detecting Adversarial Examples
Authors	Alessandro Cennamo, Ido Freeman, Anton Kummert
Abstract	Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the topic, providing both cutting edge-attack techniques and various defensive strategies. In this work, we focus on the development of a system capable of detecting adversarial samples by exploiting statistical information from the training-set. Our detector computes several distorted replicas of the test input, then collects the classifier’s prediction vectors to build a meaningful signature for the detection task. Then, the signature is projected onto the class-specific statistic vector to infer the input’s nature. The classification output of the original input is used to select the class-statistic vector. We show that our method reliably detects malicious inputs, outperforming state-of-the-art approaches in various settings, while being complementary to other defensive solutions.
Tasks
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09705v1
PDF	https://arxiv.org/pdf/1908.09705v1.pdf
PWC	https://paperswithcode.com/paper/a-statistical-defense-approach-for-detecting
Repo
Framework

Concise and Effective Network for 3D Human Modeling from Orthogonal Silhouettes


Title	Concise and Effective Network for 3D Human Modeling from Orthogonal Silhouettes
Authors	Bin Liu, Xiuping Liu, Zhixin Yang, Charlie C. L. Wang
Abstract	In this paper, we revisit the problem of 3D human modeling from two orthogonal silhouettes of individuals (i.e., front and side views). Different from our prior work, a supervised learning approach based on \textit{convolutional neural network} (CNN) is investigated to solve the problem by establishing a mapping function that can effectively extract features from two silhouettes and fuse them into coefficients in the shape space of human bodies. A new CNN structure is proposed in our work to exact not only the discriminative features of front and side views and also their mixed features for the mapping function. 3D human models with high accuracy are synthesized from coefficients generated by the mapping function. Existing CNN approaches for 3D human modeling usually learn a large number of parameters (from 8M to 350M) from two binary images. Differently, we investigate a new network architecture and conduct the samples on silhouettes as input. As a consequence, more accurate models can be generated by our network with only 2.5M coefficients. The training of our network is conducted on samples obtained by augmenting a publicly accessible dataset. Learning transfer by using datasets with a smaller number of scanned models is applied to our network to enable the function of generating results with gender-oriented (or geographical) patterns.
Tasks
Published	2019-12-25
URL	https://arxiv.org/abs/1912.11616v1
PDF	https://arxiv.org/pdf/1912.11616v1.pdf
PWC	https://paperswithcode.com/paper/concise-and-effective-network-for-3d-human
Repo
Framework

Understanding the Radical Mind: Identifying Signals to Detect Extremist Content on Twitter


Title	Understanding the Radical Mind: Identifying Signals to Detect Extremist Content on Twitter
Authors	Mariam Nouh, Jason R. C. Nurse, Michael Goldsmith
Abstract	The Internet and, in particular, Online Social Networks have changed the way that terrorist and extremist groups can influence and radicalise individuals. Recent reports show that the mode of operation of these groups starts by exposing a wide audience to extremist material online, before migrating them to less open online platforms for further radicalization. Thus, identifying radical content online is crucial to limit the reach and spread of the extremist narrative. In this paper, our aim is to identify measures to automatically detect radical content in social media. We identify several signals, including textual, psychological and behavioural, that together allow for the classification of radical messages. Our contribution is three-fold: (1) we analyze propaganda material published by extremist groups and create a contextual text-based model of radical content, (2) we build a model of psychological properties inferred from these material, and (3) we evaluate these models on Twitter to determine the extent to which it is possible to automatically identify online radical tweets. Our results show that radical users do exhibit distinguishable textual, psychological, and behavioural properties. We find that the psychological properties are among the most distinguishing features. Additionally, our results show that textual models using vector embedding features significantly improves the detection over TF-IDF features. We validate our approach on two experiments achieving high accuracy. Our findings can be utilized as signals for detecting online radicalization activities.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.08067v1
PDF	https://arxiv.org/pdf/1905.08067v1.pdf
PWC	https://paperswithcode.com/paper/understanding-the-radical-mind-identifying
Repo
Framework

HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion


Title	HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion
Authors	Jiaming Shen, Zeqiu Wu, Dongming Lei, Chao Zhang, Xiang Ren, Michelle T. Vanni, Brian M. Sadler, Jiawei Han
Abstract	Taxonomies are of great value to many knowledge-rich applications. As the manual taxonomy curation costs enormous human effects, automatic taxonomy construction is in great demand. However, most existing automatic taxonomy construction methods can only build hypernymy taxonomies wherein each edge is limited to expressing the “is-a” relation. Such a restriction limits their applicability to more diverse real-world tasks where the parent-child may carry different relations. In this paper, we aim to construct a task-guided taxonomy from a domain-specific corpus and allow users to input a “seed” taxonomy, serving as the task guidance. We propose an expansion-based taxonomy construction framework, namely HiExpan, which automatically generates key term list from the corpus and iteratively grows the seed taxonomy. Specifically, HiExpan views all children under each taxonomy node forming a coherent set and builds the taxonomy by recursively expanding all these sets. Furthermore, HiExpan incorporates a weakly-supervised relation extraction module to extract the initial children of a newly-expanded node and adjusts the taxonomy tree by optimizing its global structure. Our experiments on three real datasets from different domains demonstrate the effectiveness of HiExpan for building task-guided taxonomies.
Tasks	Relation Extraction
Published	2019-10-17
URL	https://arxiv.org/abs/1910.08194v1
PDF	https://arxiv.org/pdf/1910.08194v1.pdf
PWC	https://paperswithcode.com/paper/hiexpan-task-guided-taxonomy-construction-by
Repo
Framework

Momentum in Reinforcement Learning


Title	Momentum in Reinforcement Learning
Authors	Nino Vieillard, Bruno Scherrer, Olivier Pietquin, Matthieu Geist
Abstract	We adapt the optimization’s concept of momentum to reinforcement learning. Seeing the state-action value functions as an analog to the gradients in optimization, we interpret momentum as an average of consecutive $q$-functions. We derive Momentum Value Iteration (MoVI), a variation of Value Iteration that incorporates this momentum idea. Our analysis shows that this allows MoVI to average errors over successive iterations. We show that the proposed approach can be readily extended to deep learning. Specifically, we propose a simple improvement on DQN based on MoVI, and experiment it on Atari games.
Tasks	Atari Games
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09322v2
PDF	https://arxiv.org/pdf/1910.09322v2.pdf
PWC	https://paperswithcode.com/paper/momentum-in-reinforcement-learning
Repo
Framework

“Going on a vacation” takes longer than “Going for a walk”: A Study of Temporal Commonsense Understanding


Title	“Going on a vacation” takes longer than “Going for a walk”: A Study of Temporal Commonsense Understanding
Authors	Ben Zhou, Daniel Khashabi, Qiang Ning, Dan Roth
Abstract	Understanding time is crucial for understanding events expressed in natural language. Because people rarely say the obvious, it is often necessary to have commonsense knowledge about various temporal aspects of events, such as duration, frequency, and temporal order. However, this important problem has so far received limited attention. This paper systematically studies this temporal commonsense problem. Specifically, we define five classes of temporal commonsense, and use crowdsourcing to develop a new dataset, MCTACO, that serves as a test set for this task. We find that the best current methods used on MCTACO are still far behind human performance, by about 20%, and discuss several directions for improvement. We hope that the new dataset and our study here can foster more future research on this topic.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.03065v1
PDF	https://arxiv.org/pdf/1909.03065v1.pdf
PWC	https://paperswithcode.com/paper/going-on-a-vacation-takes-longer-than-going
Repo
Framework

Variational Gaussian Processes with Signature Covariances


Title	Variational Gaussian Processes with Signature Covariances
Authors	Csaba Toth, Harald Oberhauser
Abstract	We introduce a Bayesian approach to learn from stream-valued data by using Gaussian processes with the recently introduced signature kernel as covariance function. To cope with the computational complexity in time and memory that arises with long streams that evolve in large state spaces, we develop a variational Bayes approach with sparse inducing tensors. We provide an implementation based on GPFlow and benchmark this variational Gaussian process model on supervised classification tasks for time series and text (a stream of words).
Tasks	Gaussian Processes, Time Series
Published	2019-06-19
URL	https://arxiv.org/abs/1906.08215v1
PDF	https://arxiv.org/pdf/1906.08215v1.pdf
PWC	https://paperswithcode.com/paper/variational-gaussian-processes-with-signature
Repo
Framework

Enumerating Range Modes


Title	Enumerating Range Modes
Authors	Kentaro Sumigawa, Sankardeep Chakraborty, Kunihiko Sadakane, Srinivasa Rao Satti
Abstract	We consider the range mode problem where given a sequence and a query range in it, we want to find items with maximum frequency in the range. We give time- and space- efficient algorithms for this problem. Our algorithms are efficient for small maximum frequency cases. We also consider a natural generalization of the problem: the range mode enumeration problem, for which there has been no known efficient algorithms. Our algorithms have query time complexities which is linear to the output size plus small terms.
Tasks
Published	2019-07-25
URL	https://arxiv.org/abs/1907.10984v1
PDF	https://arxiv.org/pdf/1907.10984v1.pdf
PWC	https://paperswithcode.com/paper/enumerating-range-modes
Repo
Framework

AI-based evaluation of the SDGs: The case of crop detection with earth observation data


Title	AI-based evaluation of the SDGs: The case of crop detection with earth observation data
Authors	Natalia Efremova, Dennis West, Dmitry Zausaev
Abstract	The framework of the seventeen sustainable development goals is a challenge for developers and researchers applying artificial intelligence (AI). AI and earth observations (EO) can provide reliable and disaggregated data for better monitoring of the sustainable development goals (SDGs). In this paper, we present an overview of SDG targets, which can be effectively measured with AI tools. We identify indicators with the most significant contribution from the AI and EO and describe an application of state-of-the-art machine learning models to one of the indicators. We describe an application of U-net with SE blocks for efficient segmentation of satellite imagery for crop detection. Finally, we demonstrate how AI can be more effectively applied in solutions directly contributing towards specific SDGs and propose further research on an AI-based evaluative infrastructure for SDGs.
Tasks
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02813v1
PDF	https://arxiv.org/pdf/1907.02813v1.pdf
PWC	https://paperswithcode.com/paper/ai-based-evaluation-of-the-sdgs-the-case-of
Repo
Framework

On the Quantization of Cellular Neural Networks for Cyber-Physical Systems


Title	On the Quantization of Cellular Neural Networks for Cyber-Physical Systems
Authors	Xiaowei Xu
Abstract	Cyber-Physical Systems (CPSs) have been pervasive including smart grid, autonomous automobile systems, medical monitoring, process control systems, robotics systems, and automatic pilot avionics. As usually implemented on embedded devices, CPS is typically constrained by computation capacity and energy consumption. In some CPS applications such as telemedicine and advanced driving assistance system (ADAS), data processing on the embedded devices is preferred due to security/safety and real-time requirement. Therefore, high efficiency is highly desirable for such CPS applications. In this paper we present CeNN quantization for high-efficient processing for CPS applications, particularly telemedicine and ADAS applications. We systematically put forward powers-of-two based incremental quantization of CeNNs for efficient hardware implementation. The incremental quantization contains iterative procedures including parameter partition, parameter quantization, and re-training. We propose five different strategies including random strategy, pruning inspired strategy, weighted pruning inspired strategy, nearest neighbor strategy, and weighted nearest neighbor strategy. Experimental results show that our approach can achieve a speedup up to 7.8x with no performance loss compared with the state-of-the-art FPGA solutions for CeNNs.
Tasks	Quantization
Published	2019-03-05
URL	http://arxiv.org/abs/1903.02048v1
PDF	http://arxiv.org/pdf/1903.02048v1.pdf
PWC	https://paperswithcode.com/paper/on-the-quantization-of-cellular-neural
Repo
Framework

Imminent Collision Mitigation with Reinforcement Learning and Vision


Title	Imminent Collision Mitigation with Reinforcement Learning and Vision
Authors	Horia Porav, Paul Newman
Abstract	This work examines the role of reinforcement learning in reducing the severity of on-road collisions by controlling velocity and steering in situations in which contact is imminent. We construct a model, given camera images as input, that is capable of learning and predicting the dynamics of obstacles, cars and pedestrians, and train our policy using this model. Two policies that control both braking and steering are compared against a baseline where the only action taken is (conventional) braking in a straight line. The two policies are trained using two distinct reward structures, one where any and all collisions incur a fixed penalty, and a second one where the penalty is calculated based on already established delta-v models of injury severity. The results show that both policies exceed the performance of the baseline, with the policy trained using injury models having the highest performance.
Tasks
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00898v1
PDF	http://arxiv.org/pdf/1901.00898v1.pdf
PWC	https://paperswithcode.com/paper/imminent-collision-mitigation-with
Repo
Framework

re-OBJ: Jointly Learning the Foreground and Background for Object Instance Re-identification


Title	re-OBJ: Jointly Learning the Foreground and Background for Object Instance Re-identification
Authors	Vaibhav Bansal, Stuart James, Alessio Del Bue
Abstract	Conventional approaches to object instance re-identification rely on matching appearances of the target objects among a set of frames. However, learning appearances of the objects alone might fail when there are multiple objects with similar appearance or multiple instances of same object class present in the scene. This paper proposes that partial observations of the background can be utilized to aid in the object re-identification task for a rigid scene, especially a rigid environment with a lot of reoccurring identical models of objects. Using an extension to the Mask R-CNN architecture, we learn to encode the important and distinct information in the background jointly with the foreground relevant to rigid real-world scenarios such as an indoor environment where objects are static and the camera moves around the scene. We demonstrate the effectiveness of our joint visual feature in the re-identification of objects in the ScanNet dataset and show a relative improvement of around 28.25% in the rank-1 accuracy over the deepSort method.
Tasks
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07704v2
PDF	https://arxiv.org/pdf/1909.07704v2.pdf
PWC	https://paperswithcode.com/paper/re-obj-jointly-learning-the-foreground-and
Repo
Framework

Beyond Similarity: Relation Embedding with Dual Attentions for Item-based Recommendation


Title	Beyond Similarity: Relation Embedding with Dual Attentions for Item-based Recommendation
Authors	Liang Zhang, Guannan Liu, Junjie Wu
Abstract	Given the effectiveness and ease of use, Item-based Collaborative Filtering (ICF) methods have been broadly used in industry in recent years. The key of ICF lies in the similarity measurement between items, which however is a coarse-grained numerical value that can hardly capture users’ fine-grained preferences toward different latent aspects of items from a representation learning perspective. In this paper, we propose a model called REDA (latent Relation Embedding with Dual Attentions) to address this challenge. REDA is essentially a deep learning based recommendation method that employs an item relation embedding scheme through a neural network structure for inter-item relations representation. A relational user embedding is then proposed by aggregating the relation embeddings between all purchased items of a user, which not only better characterizes user preferences but also alleviates the data sparsity problem. Moreover, to capture valid meta-knowledge that reflects users’ desired latent aspects and meanwhile suppress their explosive growth towards overfitting, we further propose a dual attentions mechanism, including a memory attention and a weight attention. A relation-wise optimization method is finally developed for model inference by constructing a personalized ranking loss for item relations. Extensive experiments are implemented on real-world datasets and the proposed model is shown to greatly outperform state-of-the-art methods, especially when the data is sparse.
Tasks	Representation Learning
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04099v1
PDF	https://arxiv.org/pdf/1911.04099v1.pdf
PWC	https://paperswithcode.com/paper/beyond-similarity-relation-embedding-with
Repo
Framework

Bounding Data-driven Model Errors in Power Grid Analysis


Title	Bounding Data-driven Model Errors in Power Grid Analysis
Authors	Yuxiao Liu, Bolun Xu, Audun Botterud, Ning Zhang, Chongqing Kang
Abstract	Data-driven models analyze power grids under incomplete physical information, and their accuracy has been mostly validated empirically using certain training and testing datasets. This paper explores error bounds for data-driven models under all possible training and testing scenarios, and proposes an evaluation implementation based on Rademacher complexity theory. We answer key questions for data-driven models: how much training data is required to guarantee a certain error bound, and how partial physical knowledge can be utilized to reduce the required amount of data. Our results are crucial for the evaluation and application of data-driven models in power grid analysis. We demonstrate the proposed method by finding generalization error bounds for two applications, i.e. branch flow linearization and external network equivalent under different degrees of physical knowledge. Results identify how the bounds decrease with additional power grid physical knowledge or more training data.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1910.13613v1
PDF	https://arxiv.org/pdf/1910.13613v1.pdf
PWC	https://paperswithcode.com/paper/bounding-data-driven-model-errors-in-power
Repo
Framework

Teaching on a Budget in Multi-Agent Deep Reinforcement Learning


Title	Teaching on a Budget in Multi-Agent Deep Reinforcement Learning
Authors	Ercüment İlhan, Jeremy Gow, Diego Perez-Liebana
Abstract	Deep Reinforcement Learning (RL) algorithms can solve complex sequential decision tasks successfully. However, they have a major drawback of having poor sample efficiency which can often be tackled by knowledge reuse. In Multi-Agent Reinforcement Learning (MARL) this drawback becomes worse, but at the same time, a new set of opportunities to leverage knowledge are also presented through agent interactions. One promising approach among these is peer-to-peer action advising through a teacher-student framework. Despite being introduced for single-agent RL originally, recent studies show that it can also be applied to multi-agent scenarios with promising empirical results. However, studies in this line of research are currently very limited. In this paper, we propose heuristics-based action advising techniques in cooperative decentralised MARL, using a nonlinear function approximation based task-level policy. By adopting Random Network Distillation technique, we devise a measurement for agents to assess their knowledge in any given state and be able to initiate the teacher-student dynamics with no prior role assumptions. Experimental results in a gridworld environment show that such an approach may indeed be useful and needs to be further investigated.
Tasks	Multi-agent Reinforcement Learning
Published	2019-04-19
URL	https://arxiv.org/abs/1905.01357v2
PDF	https://arxiv.org/pdf/1905.01357v2.pdf
PWC	https://paperswithcode.com/paper/190501357
Repo
Framework