January 30, 2020

3023 words 15 mins read

Paper Group ANR 356

MolecularRNN: Generating realistic molecular graphs with optimized properties. Deep Fitting Degree Scoring Network for Monocular 3D Object Detection. Voice command generation using Progressive Wavegans. A survey on acoustic sensing. Group-Connected Multilayer Perceptron Networks. Contrastive Reasons Detection and Clustering from Online Polarized De …

MolecularRNN: Generating realistic molecular graphs with optimized properties


Title	MolecularRNN: Generating realistic molecular graphs with optimized properties
Authors	Mariya Popova, Mykhailo Shvets, Junier Oliva, Olexandr Isayev
Abstract	Designing new molecules with a set of predefined properties is a core problem in modern drug discovery and development. There is a growing need for de-novo design methods that would address this problem. We present MolecularRNN, the graph recurrent generative model for molecular structures. Our model generates diverse realistic molecular graphs after likelihood pretraining on a big database of molecules. We perform an analysis of our pretrained models on large-scale generated datasets of 1 million samples. Further, the model is tuned with policy gradient algorithm, provided a critic that estimates the reward for the property of interest. We show a significant distribution shift to the desired range for lipophilicity, drug-likeness, and melting point outperforming state-of-the-art works. With the use of rejection sampling based on valency constraints, our model yields 100% validity. Moreover, we show that invalid molecules provide a rich signal to the model through the use of structure penalty in our reinforcement learning pipeline.
Tasks	Drug Discovery
Published	2019-05-31
URL	https://arxiv.org/abs/1905.13372v1
PDF	https://arxiv.org/pdf/1905.13372v1.pdf
PWC	https://paperswithcode.com/paper/molecularrnn-generating-realistic-molecular
Repo
Framework

Deep Fitting Degree Scoring Network for Monocular 3D Object Detection


Title	Deep Fitting Degree Scoring Network for Monocular 3D Object Detection
Authors	Lijie Liu, Jiwen Lu, Chunjing Xu, Qi Tian, Jie Zhou
Abstract	In this paper, we propose to learn a deep fitting degree scoring network for monocular 3D object detection, which aims to score fitting degree between proposals and object conclusively. Different from most existing monocular frameworks which use tight constraint to get 3D location, our approach achieves high-precision localization through measuring the visual fitting degree between the projected 3D proposals and the object. We first regress the dimension and orientation of the object using an anchor-based method so that a suitable 3D proposal can be constructed. We propose FQNet, which can infer the 3D IoU between the 3D proposals and the object solely based on 2D cues. Therefore, during the detection process, we sample a large number of candidates in the 3D space and project these 3D bounding boxes on 2D image individually. The best candidate can be picked out by simply exploring the spatial overlap between proposals and the object, in the form of the output 3D IoU score of FQNet. Experiments on the KITTI dataset demonstrate the effectiveness of our framework.
Tasks	3D Object Detection, Object Detection
Published	2019-04-26
URL	https://arxiv.org/abs/1904.12681v2
PDF	https://arxiv.org/pdf/1904.12681v2.pdf
PWC	https://paperswithcode.com/paper/deep-fitting-degree-scoring-network-for
Repo
Framework

Voice command generation using Progressive Wavegans


Title	Voice command generation using Progressive Wavegans
Authors	Thomas Wiest, Nicholas Cummins, Alice Baird, Simone Hantke, Judith Dineley, Björn Schuller
Abstract	Generative Adversarial Networks (GANs) have become exceedingly popular in a wide range of data-driven research fields, due in part to their success in image generation. Their ability to generate new samples, often from only a small amount of input data, makes them an exciting research tool in areas with limited data resources. One less-explored application of GANs is the synthesis of speech and audio samples. Herein, we propose a set of extensions to the WaveGAN paradigm, a recently proposed approach for sound generation using GANs. The aim of these extensions - preprocessing, Audio-to-Audio generation, skip connections and progressive structures - is to improve the human likeness of synthetic speech samples. Scores from listening tests with 30 volunteers demonstrated a moderate improvement (Cohen’s d coefficient of 0.65) in human likeness using the proposed extensions compared to the original WaveGAN approach.
Tasks	Audio Generation, Image Generation
Published	2019-03-13
URL	http://arxiv.org/abs/1903.07395v1
PDF	http://arxiv.org/pdf/1903.07395v1.pdf
PWC	https://paperswithcode.com/paper/voice-command-generation-using-progressive
Repo
Framework

A survey on acoustic sensing


Title	A survey on acoustic sensing
Authors	Chao Cai, Rong Zheng, Menglan Hu
Abstract	The rise of Internet-of-Things (IoT) has brought many new sensing mechanisms. Among these mechanisms, acoustic sensing attracts much attention in recent years. Acoustic sensing exploits acoustic sensors beyond their primary uses, namely recording and playing, to enable interesting applications and new user experience. In this paper, we present the first survey of recent advances in acoustic sensing using commodity hardware. We propose a general framework that categorizes main building blocks of acoustic sensing systems. This framework consists of three layers, i.e., the physical layer, processing layer, and application layer. We highlight different sensing approaches in the processing layer and fundamental design considerations in the physical layer. Many existing and potential applications including context-aware applications, human-computer interface, and aerial acoustic communications are presented in depth. Challenges and future research trends are also discussed.
Tasks
Published	2019-01-11
URL	http://arxiv.org/abs/1901.03450v1
PDF	http://arxiv.org/pdf/1901.03450v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-on-acoustic-sensing
Repo
Framework

Group-Connected Multilayer Perceptron Networks


Title	Group-Connected Multilayer Perceptron Networks
Authors	Mohammad Kachuee, Sajad Darabi, Shayan Fazeli, Majid Sarrafzadeh
Abstract	Despite the success of deep learning in domains such as image, voice, and graphs, there has been little progress in deep representation learning for domains without a known structure between features. For instance, a tabular dataset of different demographic and clinical factors where the feature interactions are not given as a prior. In this paper, we propose Group-Connected Multilayer Perceptron (GMLP) networks to enable deep representation learning in these domains. GMLP is based on the idea of learning expressive feature combinations (groups) and exploiting them to reduce the network complexity by defining local group-wise operations. During the training phase, GMLP learns a sparse feature grouping matrix using temperature annealing softmax with an added entropy loss term to encourage the sparsity. Furthermore, an architecture is suggested which resembles binary trees, where group-wise operations are followed by pooling operations to combine information; reducing the number of groups as the network grows in depth. To evaluate the proposed method, we conducted experiments on five different real-world datasets covering various application areas. Additionally, we provide visualizations on MNIST and synthesized data. According to the results, GMLP is able to successfully learn and exploit expressive feature combinations and achieve state-of-the-art classification performance on different datasets.
Tasks	Representation Learning
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09600v1
PDF	https://arxiv.org/pdf/1912.09600v1.pdf
PWC	https://paperswithcode.com/paper/group-connected-multilayer-perceptron-1
Repo
Framework

Contrastive Reasons Detection and Clustering from Online Polarized Debate


Title	Contrastive Reasons Detection and Clustering from Online Polarized Debate
Authors	Amine Trabelsi, Osmar R. Zaiane
Abstract	This work tackles the problem of unsupervised modeling and extraction of the main contrastive sentential reasons conveyed by divergent viewpoints on polarized issues. It proposes a pipeline approach centered around the detection and clustering of phrases, assimilated to argument facets using a novel Phrase Author Interaction Topic-Viewpoint model. The evaluation is based on the informativeness, the relevance and the clustering accuracy of extracted reasons. The pipeline approach shows a significant improvement over state-of-the-art methods in contrastive summarization on online debate datasets.
Tasks
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00648v1
PDF	https://arxiv.org/pdf/1908.00648v1.pdf
PWC	https://paperswithcode.com/paper/contrastive-reasons-detection-and-clustering
Repo
Framework

Appending Adversarial Frames for Universal Video Attack


Title	Appending Adversarial Frames for Universal Video Attack
Authors	Zhikai Chen, Lingxi Xie, Shanmin Pang, Yong He, Qi Tian
Abstract	There have been many efforts in attacking image classification models with adversarial perturbations, but the same topic on video classification has not yet been thoroughly studied. This paper presents a novel idea of video-based attack, which appends a few dummy frames (e.g., containing the texts of `thanks for watching’) to a video clip and then adds adversarial perturbations only on these new frames. Our approach enjoys three major benefits, namely, a high success rate, a low perceptibility, and a strong ability in transferring across different networks. These benefits mostly come from the common dummy frame which pushes all samples towards the boundary of classification. On the other hand, such attacks are easily to be concealed since most people would not notice the abnormality behind the perturbed video clips. We perform experiments on two popular datasets with six state-of-the-art video classification models, and demonstrate the effectiveness of our approach in the scenario of universal video attacks. \|
Tasks	Image Classification, Video Classification
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04538v1
PDF	https://arxiv.org/pdf/1912.04538v1.pdf
PWC	https://paperswithcode.com/paper/appending-adversarial-frames-for-universal
Repo
Framework

Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance


Title	Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance
Authors	Mingxuan Jing, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Chao Yang, Bin Fang, Huaping Liu
Abstract	In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be perfect and sufficient, which yet is unrealistic to meet in practice. To work on imperfect demonstrations, we first define an imperfect expert setting for RLfD in a formal way, and then point out that previous methods suffer from two issues in terms of optimality and convergence, respectively. Upon the theoretical findings we have derived, we tackle these two issues by regarding the expert guidance as a soft constraint on regulating the policy exploration of the agent, which eventually leads to a constrained optimization problem. We further demonstrate that such problem is able to be addressed efficiently by performing a local linear search on its dual form. Considerable empirical evaluations on a comprehensive collection of benchmarks indicate our method attains consistent improvement over other RLfD counterparts.
Tasks
Published	2019-11-16
URL	https://arxiv.org/abs/1911.07109v2
PDF	https://arxiv.org/pdf/1911.07109v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-from-imperfect-2
Repo
Framework

Location, Occupation, and Semantics based Socioeconomic Status Inference on Twitter


Title	Location, Occupation, and Semantics based Socioeconomic Status Inference on Twitter
Authors	Jacobo Levy Abitbol, Márton Karsai, Eric Fleury
Abstract	The socioeconomic status of people depends on a combination of individual characteristics and environmental variables, thus its inference from online behavioral data is a difficult task. Attributes like user semantics in communication, habitat, occupation, or social network are all known to be determinant predictors of this feature. In this paper we propose three different data collection and combination methods to first estimate and, in turn, infer the socioeconomic status of French Twitter users from their online semantics. Our methods are based on open census data, crawled professional profiles, and remotely sensed, expert annotated information on living environment. Our inference models reach similar performance of earlier results with the advantage of relying on broadly available datasets and of providing a generalizable framework to estimate socioeconomic status of large numbers of Twitter users. These results may contribute to the scientific discussion on social stratification and inequalities, and may fuel several applications.
Tasks
Published	2019-01-16
URL	http://arxiv.org/abs/1901.05389v1
PDF	http://arxiv.org/pdf/1901.05389v1.pdf
PWC	https://paperswithcode.com/paper/location-occupation-and-semantics-based
Repo
Framework

Simultaneous Segmentation and Recognition: Towards more accurate Ego Gesture Recognition


Title	Simultaneous Segmentation and Recognition: Towards more accurate Ego Gesture Recognition
Authors	Tejo Chalasani, Aljosa Smolic
Abstract	Ego hand gestures can be used as an interface in AR and VR environments. While the context of an image is important for tasks like scene understanding, object recognition, image caption generation and activity recognition, it plays a minimal role in ego hand gesture recognition. An ego hand gesture used for AR and VR environments conveys the same information regardless of the background. With this idea in mind, we present our work on ego hand gesture recognition that produces embeddings from RBG images with ego hands, which are simultaneously used for ego hand segmentation and ego gesture recognition. To this extent, we achieved better recognition accuracy (96.9%) compared to the state of the art (92.2%) on the biggest ego hand gesture dataset available publicly. We present a gesture recognition deep neural network which recognises ego hand gestures from videos (videos containing a single gesture) by generating and recognising embeddings of ego hands from image sequences of varying length. We introduce the concept of simultaneous segmentation and recognition applied to ego hand gestures, present the network architecture, the training procedure and the results compared to the state of the art on the EgoGesture dataset
Tasks	Activity Recognition, Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition, Hand Segmentation, Object Recognition, Scene Understanding
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08606v1
PDF	https://arxiv.org/pdf/1909.08606v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-segmentation-and-recognition
Repo
Framework

Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples


Title	Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples
Authors	Tengyu Xu, Shaofeng Zou, Yingbin Liang
Abstract	Gradient-based temporal difference (GTD) algorithms are widely used in off-policy learning scenarios. Among them, the two time-scale TD with gradient correction (TDC) algorithm has been shown to have superior performance. In contrast to previous studies that characterized the non-asymptotic convergence rate of TDC only under identical and independently distributed (i.i.d.) data samples, we provide the first non-asymptotic convergence analysis for two time-scale TDC under a non-i.i.d.\ Markovian sample path and linear function approximation. We show that the two time-scale TDC can converge as fast as O(log t/(t^(2/3))) under diminishing stepsize, and can converge exponentially fast under constant stepsize, but at the cost of a non-vanishing error. We further propose a TDC algorithm with blockwisely diminishing stepsize, and show that it asymptotically converges with an arbitrarily small error at a blockwisely linear convergence rate. Our experiments demonstrate that such an algorithm converges as fast as TDC under constant stepsize, and still enjoys comparable accuracy as TDC under diminishing stepsize.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11907v1
PDF	https://arxiv.org/pdf/1909.11907v1.pdf
PWC	https://paperswithcode.com/paper/two-time-scale-off-policy-td-learning-non
Repo
Framework

Balancing the Tradeoff between Profit and Fairness in Rideshare Platforms During High-Demand Hours


Title	Balancing the Tradeoff between Profit and Fairness in Rideshare Platforms During High-Demand Hours
Authors	Vedant Nanda, Pan Xu, Karthik Abinav Sankararaman, John P. Dickerson, Aravind Srinivasan
Abstract	Rideshare platforms, when assigning requests to drivers, tend to maximize profit for the system and/or minimize waiting time for riders. Such platforms can exacerbate biases that drivers may have over certain types of requests. We consider the case of peak hours when the demand for rides is more than the supply of drivers. Drivers are well aware of their advantage during the peak hours and can choose to be selective about which rides to accept. Moreover, if in such a scenario, the assignment of requests to drivers (by the platform) is made only to maximize profit and/or minimize wait time for riders, requests of a certain type (e.g. from a non-popular pickup location, or to a non-popular drop-off location) might never be assigned to a driver. Such a system can be highly unfair to riders. However, increasing fairness might come at a cost of the overall profit made by the rideshare platform. To balance these conflicting goals, we present a flexible, non-adaptive algorithm, \lpalg, that allows the platform designer to control the profit and fairness of the system via parameters $\alpha$ and $\beta$ respectively. We model the matching problem as an online bipartite matching where the set of drivers is offline and requests arrive online. Upon the arrival of a request, we use \lpalg to assign it to a driver (the driver might then choose to accept or reject it) or reject the request. We formalize the measures of profit and fairness in our setting and show that by using \lpalg, the competitive ratios for profit and fairness measures would be no worse than $\alpha/e$ and $\beta/e$ respectively. Extensive experimental results on both real-world and synthetic datasets confirm the validity of our theoretical lower bounds. Additionally, they show that $\lpalg$ under some choice of $(\alpha, \beta)$ can beat two natural heuristics, Greedy and Uniform, on \emph{both} fairness and profit.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08388v1
PDF	https://arxiv.org/pdf/1912.08388v1.pdf
PWC	https://paperswithcode.com/paper/balancing-the-tradeoff-between-profit-and
Repo
Framework

Probabilistic smallest enclosing ball in high dimensions via subgradient sampling


Title	Probabilistic smallest enclosing ball in high dimensions via subgradient sampling
Authors	Amer Krivošija, Alexander Munteanu
Abstract	We study a variant of the median problem for a collection of point sets in high dimensions. This generalizes the geometric median as well as the (probabilistic) smallest enclosing ball (pSEB) problems. Our main objective and motivation is to improve the previously best algorithm for the pSEB problem by reducing its exponential dependence on the dimension to linear. This is achieved via a novel combination of sampling techniques for clustering problems in metric spaces with the framework of stochastic subgradient descent. As a result, the algorithm becomes applicable to shape fitting problems in Hilbert spaces of unbounded dimension via kernel functions. We present an exemplary application by extending the support vector data description (SVDD) shape fitting method to the probabilistic case. This is done by simulating the pSEB algorithm implicitly in the feature space induced by the kernel function.
Tasks
Published	2019-02-28
URL	http://arxiv.org/abs/1902.10966v1
PDF	http://arxiv.org/pdf/1902.10966v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-smallest-enclosing-ball-in-high
Repo
Framework

Metric Learning on Manifolds


Title	Metric Learning on Manifolds
Authors	Max Aalto, Nakul Verma
Abstract	Recent literature has shown that symbolic data, such as text and graphs, is often better represented by points on a curved manifold, rather than in Euclidean space. However, geometrical operations on manifolds are generally more complicated than in Euclidean space, and thus many techniques for processing and analysis taken for granted in Euclidean space are difficult on manifolds. A priori, it is not obvious how we may generalize such methods to manifolds. We consider specifically the problem of distance metric learning, and present a framework that solves it on a large class of manifolds, such that similar data are located in closer proximity with respect to the manifold distance function. In particular, we extend the existing metric learning algorithms, and derive the corresponding sample complexity rates for the case of manifolds. Additionally, we demonstrate an improvement of performance in $k$-means clustering and $k$-nearest neighbor classification on real-world complex networks using our methods.
Tasks	Metric Learning
Published	2019-02-05
URL	http://arxiv.org/abs/1902.01738v1
PDF	http://arxiv.org/pdf/1902.01738v1.pdf
PWC	https://paperswithcode.com/paper/metric-learning-on-manifolds
Repo
Framework

About epistemic negation and world views in Epistemic Logic Programs


Title	About epistemic negation and world views in Epistemic Logic Programs
Authors	Stefania Costantini
Abstract	In this paper we consider Epistemic Logic Programs, which extend Answer Set Programming (ASP) with “epistemic operators” and “epistemic negation”, and a recent approach to the semantics of such programs in terms of World Views. We propose some observations on the existence and number of world views. We show how to exploit an extended ASP semantics in order to: (i) provide a characterization of world views, different from existing ones; (ii) query world views and query the whole set of world views.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09867v2
PDF	https://arxiv.org/pdf/1907.09867v2.pdf
PWC	https://paperswithcode.com/paper/about-epistemic-negation-and-world-views-in
Repo
Framework