Paper Group ANR 523
A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification. Searching with Consistent Prioritization for Multi-Agent Path Finding. Distributed Cartesian Power Graph Segmentation for Graphon Estimation. Autonomous Functional Locomotion in a Tendon-Driven Limb via Limited Experience. BAN: Focusing on Boundary Context for Object Detec …
A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification
Title | A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification |
Authors | Pengcheng Yang, Shuming Ma, Yi Zhang, Junyang Lin, Qi Su, Xu Sun |
Abstract | Multi-label text classification (MLTC) aims to assign multiple labels to each sample in the dataset. The labels usually have internal correlations. However, traditional methods tend to ignore the correlations between labels. In order to capture the correlations between labels, the sequence-to-sequence (Seq2Seq) model views the MLTC task as a sequence generation problem, which achieves excellent performance on this task. However, the Seq2Seq model is not suitable for the MLTC task in essence. The reason is that it requires humans to predefine the order of the output labels, while some of the output labels in the MLTC task are essentially an unordered set rather than an ordered sequence. This conflicts with the strict requirement of the Seq2Seq model for the label order. In this paper, we propose a novel sequence-to-set framework utilizing deep reinforcement learning, which not only captures the correlations between labels, but also reduces the dependence on the label order. Extensive experimental results show that our proposed method outperforms the competitive baselines by a large margin. |
Tasks | Multi-Label Text Classification, Text Classification |
Published | 2018-09-10 |
URL | http://arxiv.org/abs/1809.03118v1 |
http://arxiv.org/pdf/1809.03118v1.pdf | |
PWC | https://paperswithcode.com/paper/a-deep-reinforced-sequence-to-set-model-for |
Repo | |
Framework | |
Searching with Consistent Prioritization for Multi-Agent Path Finding
Title | Searching with Consistent Prioritization for Multi-Agent Path Finding |
Authors | Hang Ma, Daniel Harabor, Peter J. Stuckey, Jiaoyang Li, Sven Koenig |
Abstract | We study prioritized planning for Multi-Agent Path Finding (MAPF). Existing prioritized MAPF algorithms depend on rule-of-thumb heuristics and random assignment to determine a fixed total priority ordering of all agents a priori. We instead explore the space of all possible partial priority orderings as part of a novel systematic and conflict-driven combinatorial search framework. In a variety of empirical comparisons, we demonstrate state-of-the-art solution qualities and success rates, often with similar runtimes to existing algorithms. We also develop new theoretical results that explore the limitations of prioritized planning, in terms of completeness and optimality, for the first time. |
Tasks | Multi-Agent Path Finding |
Published | 2018-12-15 |
URL | http://arxiv.org/abs/1812.06356v1 |
http://arxiv.org/pdf/1812.06356v1.pdf | |
PWC | https://paperswithcode.com/paper/searching-with-consistent-prioritization-for |
Repo | |
Framework | |
Distributed Cartesian Power Graph Segmentation for Graphon Estimation
Title | Distributed Cartesian Power Graph Segmentation for Graphon Estimation |
Authors | Shitong Wei, Oscar Hernan Madrid-Padilla, James Sharpnack |
Abstract | We study an extention of total variation denoising over images to over Cartesian power graphs and its applications to estimating non-parametric network models. The power graph fused lasso (PGFL) segments a matrix by exploiting a known graphical structure, $G$, over the rows and columns. Our main results shows that for any connected graph, under subGaussian noise, the PGFL achieves the same mean-square error rate as 2D total variation denoising for signals of bounded variation. We study the use of the PGFL for denoising an observed network $H$, where we learn the graph $G$ as the $K$-nearest neighborhood graph of an estimated metric over the vertices. We provide theoretical and empirical results for estimating graphons, a non-parametric exchangeable network model, and compare to the state of the art graphon estimation methods. |
Tasks | Denoising, Graphon Estimation |
Published | 2018-05-25 |
URL | http://arxiv.org/abs/1805.09978v1 |
http://arxiv.org/pdf/1805.09978v1.pdf | |
PWC | https://paperswithcode.com/paper/distributed-cartesian-power-graph |
Repo | |
Framework | |
Autonomous Functional Locomotion in a Tendon-Driven Limb via Limited Experience
Title | Autonomous Functional Locomotion in a Tendon-Driven Limb via Limited Experience |
Authors | Ali Marjaninejad, Darío Urbina-Meléndez, Brian A. Cohn, Francisco J. Valero-Cuevas |
Abstract | Robots will become ubiquitously useful only when they can use few attempts to teach themselves to perform different tasks, even with complex bodies and in dynamical environments. Vertebrates, in fact, successfully use trial-and-error to learn multiple tasks in spite of their intricate tendon-driven anatomies. Roboticists find such tendon-driven systems particularly hard to control because they are simultaneously nonlinear, under-determined (many tendon tensions combine to produce few net joint torques), and over-determined (few joint rotations define how many tendons need to be reeled-in/payed-out). We demonstrate—for the first time in simulation and in hardware—how a model-free approach allows few-shot autonomous learning to produce effective locomotion in a 3-tendon/2-joint tendon-driven leg. Initially, an artificial neural network fed by sparsely sampled data collected using motor babbling creates an inverse map from limb kinematics to motor activations, which is analogous to juvenile vertebrates playing during development. Thereafter, iterative reward-driven exploration of candidate motor activations simultaneously refines the inverse map and finds a functional locomotor limit-cycle autonomously. This biologically-inspired algorithm, which we call G2P (General to Particular), enables versatile adaptation of robots to changes in the target task, mechanics of their bodies, and environment. Moreover, this work empowers future studies of few-shot autonomous learning in biological systems, which is the foundation of their enviable functional versatility. |
Tasks | |
Published | 2018-10-19 |
URL | http://arxiv.org/abs/1810.08615v1 |
http://arxiv.org/pdf/1810.08615v1.pdf | |
PWC | https://paperswithcode.com/paper/autonomous-functional-locomotion-in-a-tendon |
Repo | |
Framework | |
BAN: Focusing on Boundary Context for Object Detection
Title | BAN: Focusing on Boundary Context for Object Detection |
Authors | Yonghyun Kim, Taewook Kim, Bong-Nam Kang, Jieun Kim, Daijin Kim |
Abstract | Visual context is one of the important clue for object detection and the context information for boundaries of an object is especially valuable. We propose a boundary aware network (BAN) designed to exploit the visual contexts including boundary information and surroundings, named boundary context, and define three types of the boundary contexts: side, vertex and in/out-boundary context. Our BAN consists of 10 sub-networks for the area belonging to the boundary contexts. The detection head of BAN is defined as an ensemble of these sub-networks with different contributions depending on the sub-problem of detection. To verify our method, we visualize the activation of the sub-networks according to the boundary contexts and empirically show that the sub-networks contribute more to the related sub-problem in detection. We evaluate our method on PASCAL VOC detection benchmark and MS COCO dataset. The proposed method achieves the mean Average Precision (mAP) of 83.4% on PASCAL VOC and 36.9% on MS COCO. BAN allows the convolution network to provide an additional source of contexts for detection and selectively focus on the more important contexts, and it can be generally applied to many other detection methods as well to enhance the accuracy in detection. |
Tasks | Object Detection |
Published | 2018-11-13 |
URL | http://arxiv.org/abs/1811.05243v1 |
http://arxiv.org/pdf/1811.05243v1.pdf | |
PWC | https://paperswithcode.com/paper/ban-focusing-on-boundary-context-for-object |
Repo | |
Framework | |
Parallel Statistical and Machine Learning Methods for Estimation of Physical Load
Title | Parallel Statistical and Machine Learning Methods for Estimation of Physical Load |
Authors | Sergii Stirenko, Gang Peng, Wei Zeng, Yuri Gordienko, Oleg Alienin, Oleksandr Rokovyi, Nikita Gordienko |
Abstract | Several statistical and machine learning methods are proposed to estimate the type and intensity of physical load and accumulated fatigue . They are based on the statistical analysis of accumulated and moving window data subsets with construction of a kurtosis-skewness diagram. This approach was applied to the data gathered by the wearable heart monitor for various types and levels of physical activities, and for people with various physical conditions. The different levels of physical activities, loads, and fitness can be distinguished from the kurtosis-skewness diagram, and their evolution can be monitored. Several metrics for estimation of the instant effect and accumulated effect (physical fatigue) of physical loads were proposed. The data and results presented allow to extend application of these methods for modeling and characterization of complex human activity patterns, for example, to estimate the actual and accumulated physical load and fatigue, model the potential dangerous development, and give cautions and advice in real time. |
Tasks | |
Published | 2018-08-14 |
URL | http://arxiv.org/abs/1808.04760v1 |
http://arxiv.org/pdf/1808.04760v1.pdf | |
PWC | https://paperswithcode.com/paper/parallel-statistical-and-machine-learning |
Repo | |
Framework | |
Bayesian Policy Optimization for Model Uncertainty
Title | Bayesian Policy Optimization for Model Uncertainty |
Authors | Gilwoo Lee, Brian Hou, Aditya Mandalika, Jeongseok Lee, Sanjiban Choudhury, Siddhartha S. Srinivasa |
Abstract | Addressing uncertainty is critical for autonomous systems to robustly adapt to the real world. We formulate the problem of model uncertainty as a continuous Bayes-Adaptive Markov Decision Process (BAMDP), where an agent maintains a posterior distribution over latent model parameters given a history of observations and maximizes its expected long-term reward with respect to this belief distribution. Our algorithm, Bayesian Policy Optimization, builds on recent policy optimization algorithms to learn a universal policy that navigates the exploration-exploitation trade-off to maximize the Bayesian value function. To address challenges from discretizing the continuous latent parameter space, we propose a new policy network architecture that encodes the belief distribution independently from the observable state. Our method significantly outperforms algorithms that address model uncertainty without explicitly reasoning about belief distributions and is competitive with state-of-the-art Partially Observable Markov Decision Process solvers. |
Tasks | |
Published | 2018-10-01 |
URL | https://arxiv.org/abs/1810.01014v2 |
https://arxiv.org/pdf/1810.01014v2.pdf | |
PWC | https://paperswithcode.com/paper/bayesian-policy-optimization-for-model |
Repo | |
Framework | |
Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
Title | Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning |
Authors | Shruti Vyas, Yogesh S Rawat, Mubarak Shah |
Abstract | The recent success in deep learning has lead to various effective representation learning methods for videos. However, the current approaches for video representation require large amount of human labeled datasets for effective learning. We present an unsupervised representation learning framework to encode scene dynamics in videos captured from multiple viewpoints. The proposed framework has two main components: Representation Learning Network (RL-NET), which learns a representation with the help of Blending Network (BL-NET), and Video Rendering Network (VR-NET), which is used for video synthesis. The framework takes as input video clips from different viewpoints and time, learns an internal representation and uses this representation to render a video clip from an arbitrary given viewpoint and time. The ability of the proposed network to render video frames from arbitrary viewpoints and time enable it to learn a meaningful and robust representation of the scene dynamics. We demonstrate the effectiveness of the proposed method in rendering view-aware as well as time-aware video clips on two different real-world datasets including UCF-101 and NTU-RGB+D. To further validate the effectiveness of the learned representation, we use it for the task of view-invariant activity classification where we observe a significant improvement (~26%) in the performance on NTU-RGB+D dataset compared to the existing state-of-the art methods. |
Tasks | Representation Learning, Unsupervised Representation Learning |
Published | 2018-11-26 |
URL | http://arxiv.org/abs/1811.10699v2 |
http://arxiv.org/pdf/1811.10699v2.pdf | |
PWC | https://paperswithcode.com/paper/time-aware-and-view-aware-video-rendering-for |
Repo | |
Framework | |
FAKEDETECTOR: Effective Fake News Detection with Deep Diffusive Neural Network
Title | FAKEDETECTOR: Effective Fake News Detection with Deep Diffusive Neural Network |
Authors | Jiawei Zhang, Bowen Dong, Philip S. Yu |
Abstract | In recent years, due to the booming development of online social networks, fake news for various commercial and political purposes has been appearing in large numbers and widespread in the online world. With deceptive words, online social network users can get infected by these online fake news easily, which has brought about tremendous effects on the offline society already. An important goal in improving the trustworthiness of information in online social networks is to identify the fake news timely. This paper aims at investigating the principles, methodologies and algorithms for detecting fake news articles, creators and subjects from online social networks and evaluating the corresponding performance. This paper addresses the challenges introduced by the unknown characteristics of fake news and diverse connections among news articles, creators and subjects. This paper introduces a novel automatic fake news credibility inference model, namely FAKEDETECTOR. Based on a set of explicit and latent features extracted from the textual information, FAKEDETECTOR builds a deep diffusive network model to learn the representations of news articles, creators and subjects simultaneously. Extensive experiments have been done on a real-world fake news dataset to compare FAKEDETECTOR with several state-of-the-art models, and the experimental results have demonstrated the effectiveness of the proposed model. |
Tasks | Fake News Detection |
Published | 2018-05-22 |
URL | https://arxiv.org/abs/1805.08751v2 |
https://arxiv.org/pdf/1805.08751v2.pdf | |
PWC | https://paperswithcode.com/paper/fake-news-detection-with-deep-diffusive |
Repo | |
Framework | |
Active Learning for New Domains in Natural Language Understanding
Title | Active Learning for New Domains in Natural Language Understanding |
Authors | Stanislav Peshterliev, John Kearney, Abhyuday Jagannatha, Imre Kiss, Spyros Matsoukas |
Abstract | We explore active learning (AL) for improving the accuracy of new domains in a natural language understanding (NLU) system. We propose an algorithm called Majority-CRF that uses an ensemble of classification models to guide the selection of relevant utterances, as well as a sequence labeling model to help prioritize informative examples. Experiments with three domains show that Majority-CRF achieves 6.6%-9% relative error rate reduction compared to random sampling with the same annotation budget, and statistically significant improvements compared to other AL approaches. Additionally, case studies with human-in-the-loop AL on six new domains show 4.6%-9% improvement on an existing NLU system. |
Tasks | Active Learning |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.03450v2 |
http://arxiv.org/pdf/1810.03450v2.pdf | |
PWC | https://paperswithcode.com/paper/active-learning-for-new-domains-in-natural |
Repo | |
Framework | |
One-Click Annotation with Guided Hierarchical Object Detection
Title | One-Click Annotation with Guided Hierarchical Object Detection |
Authors | Adithya Subramanian, Anbumani Subramanian |
Abstract | The increase in data collection has made data annotation an interesting and valuable task in the contemporary world. This paper presents a new methodology for quickly annotating data using click-supervision and hierarchical object detection. The proposed work is semi-automatic in nature where the task of annotations is split between the human and a neural network. We show that our improved method of annotation reduces the time, cost and mental stress on a human annotator. The research also highlights how our method performs better than the current approach in different circumstances such as variation in number of objects, object size and different datasets. Our approach also proposes a new method of using object detectors making it suitable for data annotation task. The experiment conducted on PASCAL VOC dataset revealed that annotation created from our approach achieves a mAP of 0.995 and a recall of 0.903. The Our Approach has shown an overall improvement by 8.5%, 18.6% in mean average precision and recall score for KITTI and 69.6%, 36% for CITYSCAPES dataset. The proposed framework is 3-4 times faster as compared to the standard annotation method. |
Tasks | Object Detection |
Published | 2018-10-01 |
URL | http://arxiv.org/abs/1810.00609v1 |
http://arxiv.org/pdf/1810.00609v1.pdf | |
PWC | https://paperswithcode.com/paper/one-click-annotation-with-guided-hierarchical |
Repo | |
Framework | |
At Human Speed: Deep Reinforcement Learning with Action Delay
Title | At Human Speed: Deep Reinforcement Learning with Action Delay |
Authors | Vlad Firoiu, Tina Ju, Josh Tenenbaum |
Abstract | There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of tasks, from video games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning and reinforcement learning, that learn to play from experience with minimal prior knowledge. However, these machines often do not win through intelligence alone – they possess vastly superior speed and precision, allowing them to act in ways a human never could. To level the playing field, we restrict the machine’s reaction time to a human level, and find that standard deep reinforcement learning methods quickly drop in performance. We propose a solution to the action delay problem inspired by human perception – to endow agents with a neural predictive model of the environment which “undoes” the delay inherent in their environment – and demonstrate its efficacy against professional players in Super Smash Bros. Melee, a popular console fighting game. |
Tasks | Board Games |
Published | 2018-10-16 |
URL | http://arxiv.org/abs/1810.07286v1 |
http://arxiv.org/pdf/1810.07286v1.pdf | |
PWC | https://paperswithcode.com/paper/at-human-speed-deep-reinforcement-learning |
Repo | |
Framework | |
An initial study on estimating area of a leaf using image processing
Title | An initial study on estimating area of a leaf using image processing |
Authors | G. D. Illeperuma |
Abstract | Calculating leaf area is very important. Computer aided image processing can make this faster and more accurate. This include scanning the leaf , converting it to binary image and calculation of number of pixels covered. Later this is converted to mm2. |
Tasks | |
Published | 2018-07-02 |
URL | http://arxiv.org/abs/1807.00487v1 |
http://arxiv.org/pdf/1807.00487v1.pdf | |
PWC | https://paperswithcode.com/paper/an-initial-study-on-estimating-area-of-a-leaf |
Repo | |
Framework | |
On Folding and Twisting (and whatknot): towards a characterization of workspaces in syntax
Title | On Folding and Twisting (and whatknot): towards a characterization of workspaces in syntax |
Authors | Diego Gabriel Krivochen |
Abstract | Syntactic theory has traditionally adopted a constructivist approach, in which a set of atomic elements are manipulated by combinatory operations to yield derived, complex elements. Syntactic structure is thus seen as the result or discrete recursive combinatorics over lexical items which get assembled into phrases, which are themselves combined to form sentences. This view is common to European and American structuralism (e.g., Benveniste, 1971; Hockett, 1958) and different incarnations of generative grammar, transformational and non-transformational (Chomsky, 1956, 1995; and Kaplan & Bresnan, 1982; Gazdar, 1982). Since at least Uriagereka (2002), there has been some attention paid to the fact that syntactic operations must apply somewhere, particularly when copying and movement operations are considered. Contemporary syntactic theory has thus somewhat acknowledged the importance of formalizing aspects of the spaces in which elements are manipulated, but it is still a vastly underexplored area. In this paper we explore the consequences of conceptualizing syntax as a set of topological operations applying over spaces rather than over discrete elements. We argue that there are empirical advantages in such a view for the treatment of long-distance dependencies and cross-derivational dependencies: constraints on possible configurations emerge from the dynamics of the system. |
Tasks | |
Published | 2018-09-20 |
URL | http://arxiv.org/abs/1809.07853v3 |
http://arxiv.org/pdf/1809.07853v3.pdf | |
PWC | https://paperswithcode.com/paper/on-folding-and-twisting-and-whatknot-towards |
Repo | |
Framework | |
Missing Data in Sparse Transition Matrix Estimation for Sub-Gaussian Vector Autoregressive Processes
Title | Missing Data in Sparse Transition Matrix Estimation for Sub-Gaussian Vector Autoregressive Processes |
Authors | Amin Jalali, Rebecca Willett |
Abstract | High-dimensional time series data exist in numerous areas such as finance, genomics, healthcare, and neuroscience. An unavoidable aspect of all such datasets is missing data, and dealing with this issue has been an important focus in statistics, control, and machine learning. In this work, we consider a high-dimensional estimation problem where a dynamical system, governed by a stable vector autoregressive model, is randomly and only partially observed at each time point. Our task amounts to estimating the transition matrix, which is assumed to be sparse. In such a scenario, where covariates are highly interdependent and partially missing, new theoretical challenges arise. While transition matrix estimation in vector autoregressive models has been studied previously, the missing data scenario requires separate efforts. Moreover, while transition matrix estimation can be studied from a high-dimensional sparse linear regression perspective, the covariates are highly dependent and existing results on regularized estimation with missing data from i.i.d.~covariates are not applicable. At the heart of our analysis lies 1) a novel concentration result when the innovation noise satisfies the convex concentration property, as well as 2) a new quantity for characterizing the interactions of the time-varying observation process with the underlying dynamical system. |
Tasks | Time Series |
Published | 2018-02-26 |
URL | http://arxiv.org/abs/1802.09511v1 |
http://arxiv.org/pdf/1802.09511v1.pdf | |
PWC | https://paperswithcode.com/paper/missing-data-in-sparse-transition-matrix |
Repo | |
Framework | |