Paper Group ANR 104
A Simulation Study of Social-Networking-Driven Smart Recommendations for Internet of Vehicles. AED: An Anytime Evolutionary DCOP Algorithm. Featuring the topology with the unsupervised machine learning. Concentration of risk measures: A Wasserstein distance approach. Probabilistic symmetry and invariant neural networks. PolyResponse: A Rank-based A …
A Simulation Study of Social-Networking-Driven Smart Recommendations for Internet of Vehicles
| Title | A Simulation Study of Social-Networking-Driven Smart Recommendations for Internet of Vehicles |
| Authors | Kashif Zia, Arshad Muhammad, Dinesh Kumar Saini |
| Abstract | Social aspects of connectivity and information dispersion are often ignored while weighing the potential of Internet of Things (IoT). In the specialized domain of Internet of Vehicles (IoV), Social IoV (SIoV) is introduced realization its importance. Assuming a more commonly acceptable standardization of Big Data generated by IoV, the social dimensions enabling its fruitful usage remains a challenge. In this paper, an agent-based model of information sharing between vehicles for context-aware recommendations is presented. The model adheres to social dimensions as that of human society. Some important hypotheses are tested under reasonable connectivity and data constraints. The simulation results reveal that closure of social ties and its timing impacts dispersion of novel information (necessary for a recommender system) substantially. It was also observed that as the network evolves as a result of incremental interactions, recommendations guaranteeing a fair distribution of vehicles across equally good competitors is not possible. |
| Tasks | Recommendation Systems |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1907.01101v1 |
| https://arxiv.org/pdf/1907.01101v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simulation-study-of-social-networking |
| Repo | |
| Framework | |
AED: An Anytime Evolutionary DCOP Algorithm
| Title | AED: An Anytime Evolutionary DCOP Algorithm |
| Authors | Saaduddin Mahmud, Moumita Choudhury, Md. Mosaddek Khan, Long Tran-Thanh, Nicholas R. Jennings |
| Abstract | Evolutionary optimization is a generic population-based metaheuristic that can be adapted to solve a wide variety of optimization problems and has proven very effective for combinatorial optimization problems. However, the potential of this metaheuristic has not been utilized in Distributed Constraint Optimization Problems (DCOPs), a well-known class of combinatorial optimization problems prevalent in Multi-Agent Systems. In this paper, we present a novel population-based algorithm, Anytime Evolutionary DCOP (AED), that uses evolutionary optimization to solve DCOPs. In AED, the agents cooperatively construct an initial set of random solutions and gradually improve them through a new mechanism that considers an optimistic approximation of local benefits. Moreover, we present a new anytime update mechanism for AED that identifies the best among a distributed set of candidate solutions and notifies all the agents when a new best is found. In our theoretical analysis, we prove that AED is anytime. Finally, we present empirical results indicating AED outperforms the state-of-the-art DCOP algorithms in terms of solution quality. |
| Tasks | Combinatorial Optimization |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06254v3 |
| https://arxiv.org/pdf/1909.06254v3.pdf | |
| PWC | https://paperswithcode.com/paper/aed-an-anytime-evolutionary-dcop-algorithm |
| Repo | |
| Framework | |
Featuring the topology with the unsupervised machine learning
| Title | Featuring the topology with the unsupervised machine learning |
| Authors | Kenji Fukushima, Shotaro Shiba Funai, Hideaki Iida |
| Abstract | Images of line drawings are generally composed of primitive elements. One of the most fundamental elements to characterize images is the topology; line segments belong to a category different from closed circles, and closed circles with different winding degrees are nonequivalent. We investigate images with nontrivial winding using the unsupervised machine learning. We build an autoencoder model with a combination of convolutional and fully connected neural networks. We confirm that compressed data filtered from the trained model retain more than 90% of correct information on the topology, evidencing that image clustering from the unsupervised learning features the topology. |
| Tasks | Image Clustering |
| Published | 2019-08-01 |
| URL | https://arxiv.org/abs/1908.00281v1 |
| https://arxiv.org/pdf/1908.00281v1.pdf | |
| PWC | https://paperswithcode.com/paper/featuring-the-topology-with-the-unsupervised |
| Repo | |
| Framework | |
Concentration of risk measures: A Wasserstein distance approach
| Title | Concentration of risk measures: A Wasserstein distance approach |
| Authors | Sanjay P. Bhat, Prashanth L. A |
| Abstract | Known finite-sample concentration bounds for the Wasserstein distance between the empirical and true distribution of a random variable are used to derive a two-sided concentration bound for the error between the true conditional value-at-risk (CVaR) of a (possibly unbounded) random variable and a standard estimate of its CVaR computed from an i.i.d. sample. The bound applies under fairly general assumptions on the random variable, and improves upon previous bounds which were either one sided, or applied only to bounded random variables. Specializations of the bound to sub-Gaussian and sub-exponential random variables are also derived. Using a different proof technique, the results are extended to the class of spectral risk measures having a bounded risk spectrum. A similar procedure is followed to derive concentration bounds for the error between the true and estimated Cumulative Prospect Theory (CPT) value of a random variable, in cases where the random variable is bounded or sub-Gaussian. These bounds are shown to match a known bound in the bounded case, and improve upon the known bound in the sub-Gaussian case. The usefulness of the bounds is illustrated through an algorithm, and corresponding regret bound for a stochastic bandit problem, where the underlying risk measure to be optimized is CVaR. |
| Tasks | |
| Published | 2019-02-27 |
| URL | https://arxiv.org/abs/1902.10709v2 |
| https://arxiv.org/pdf/1902.10709v2.pdf | |
| PWC | https://paperswithcode.com/paper/improved-concentration-bounds-for-conditional |
| Repo | |
| Framework | |
Probabilistic symmetry and invariant neural networks
| Title | Probabilistic symmetry and invariant neural networks |
| Authors | Benjamin Bloem-Reddy, Yee Whye Teh |
| Abstract | In an effort to improve the performance of deep neural networks in data-scarce, non-i.i.d., or unsupervised settings, much recent research has been devoted to encoding invariance under symmetry transformations into neural network architectures. We treat the neural network input and output as random variables, and consider group invariance from the perspective of probabilistic symmetry. Drawing on tools from probability and statistics, we establish a link between functional and probabilistic symmetry, and obtain generative functional representations of joint and conditional probability distributions that are invariant or equivariant under the action of a compact group. Those representations completely characterize the structure of neural networks that can be used to model such distributions and yield a general program for constructing invariant stochastic or deterministic neural networks. We develop the details of the general program for exchangeable sequences and arrays, recovering a number of recent examples as special cases. |
| Tasks | |
| Published | 2019-01-18 |
| URL | http://arxiv.org/abs/1901.06082v1 |
| http://arxiv.org/pdf/1901.06082v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-symmetry-and-invariant-neural |
| Repo | |
| Framework | |
PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking
| Title | PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking |
| Authors | Matthew Henderson, Ivan Vulić, Iñigo Casanueva, Paweł Budzianowski, Daniela Gerz, Sam Coope, Georgios Spithourakis, Tsung-Hsien Wen, Nikola Mrkšić, Pei-Hao Su |
| Abstract | We present PolyResponse, a conversational search engine that supports task-oriented dialogue. It is a retrieval-based approach that bypasses the complex multi-component design of traditional task-oriented dialogue systems and the use of explicit semantics in the form of task-specific ontologies. The PolyResponse engine is trained on hundreds of millions of examples extracted from real conversations: it learns what responses are appropriate in different conversational contexts. It then ranks a large index of text and visual responses according to their similarity to the given context, and narrows down the list of relevant entities during the multi-turn conversation. We introduce a restaurant search and booking system powered by the PolyResponse engine, currently available in 8 different languages. |
| Tasks | Task-Oriented Dialogue Systems |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.01296v1 |
| https://arxiv.org/pdf/1909.01296v1.pdf | |
| PWC | https://paperswithcode.com/paper/polyresponse-a-rank-based-approach-to-task |
| Repo | |
| Framework | |
Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images
| Title | Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images |
| Authors | Valentin Gabeur, Jean-Sebastien Franco, Xavier Martin, Cordelia Schmid, Gregory Rogez |
| Abstract | In this paper, we tackle the problem of 3D human shape estimation from single RGB images. While the recent progress in convolutional neural networks has allowed impressive results for 3D human pose estimation, estimating the full 3D shape of a person is still an open issue. Model-based approaches can output precise meshes of naked under-cloth human bodies but fail to estimate details and un-modelled elements such as hair or clothing. On the other hand, non-parametric volumetric approaches can potentially estimate complete shapes but, in practice, they are limited by the resolution of the output grid and cannot produce detailed estimates. In this work, we propose a non-parametric approach that employs a double depth map to represent the 3D shape of a person: a visible depth map and a “hidden” depth map are estimated and combined, to reconstruct the human 3D shape as done with a “mould”. This representation through 2D depth maps allows a higher resolution output with a much lower dimension than voxel-based volumetric representations. Additionally, our fully derivable depth-based model allows us to efficiently incorporate a discriminator in an adversarial fashion to improve the accuracy and “humanness” of the 3D output. We train and quantitatively validate our approach on SURREAL and on 3D-HUMANS, a new photorealistic dataset made of semi-synthetic in-house videos annotated with 3D ground truth surfaces. |
| Tasks | 3D Human Pose Estimation, Pose Estimation |
| Published | 2019-08-01 |
| URL | https://arxiv.org/abs/1908.00439v1 |
| https://arxiv.org/pdf/1908.00439v1.pdf | |
| PWC | https://paperswithcode.com/paper/moulding-humans-non-parametric-3d-human-shape |
| Repo | |
| Framework | |
An Anatomy of Graph Neural Networks Going Deep via the Lens of Mutual Information: Exponential Decay vs. Full Preservation
| Title | An Anatomy of Graph Neural Networks Going Deep via the Lens of Mutual Information: Exponential Decay vs. Full Preservation |
| Authors | Nezihe Merve Gürel, Hansheng Ren, Yujing Wang, Hui Xue, Yaming Yang, Ce Zhang |
| Abstract | Graph Convolutional Network (GCN) has attracted intensive interests recently. One major limitation of GCN is that it often cannot benefit from using a deep architecture, while traditional CNN and an alternative Graph Neural Network architecture, namely GraphCNN, often achieve better quality with a deeper neural architecture. How can we explain this phenomenon? In this paper, we take the first step towards answering this question. We first conduct a systematic empirical study on the accuracy of GCN, GraphCNN, and ResNet-18 on 2D images and identified relative importance of different factors in architectural design. This inspired a novel theoretical analysis on the mutual information between the input and the output after $l$ GCN and GraphCNN layers. We identified regimes in which GCN suffers exponentially fast information lose and show that GraphCNN requires a much weaker condition for similar behavior to happen. |
| Tasks | |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04499v3 |
| https://arxiv.org/pdf/1910.04499v3.pdf | |
| PWC | https://paperswithcode.com/paper/an-anatomy-of-graph-neural-networks-going |
| Repo | |
| Framework | |
Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving
| Title | Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving |
| Authors | Sascha Rosbach, Vinit James, Simon Großjohann, Silviu Homoceanu, Stefan Roth |
| Abstract | Behavior and motion planning play an important role in automated driving. Traditionally, behavior planners instruct local motion planners with predefined behaviors. Due to the high scene complexity in urban environments, unpredictable situations may occur in which behavior planners fail to match predefined behavior templates. Recently, general-purpose planners have been introduced, combining behavior and local motion planning. These general-purpose planners allow behavior-aware motion planning given a single reward function. However, two challenges arise: First, this function has to map a complex feature space into rewards. Second, the reward function has to be manually tuned by an expert. Manually tuning this reward function becomes a tedious task. In this paper, we propose an approach that relies on human driving demonstrations to automatically tune reward functions. This study offers important insights into the driving style optimization of general-purpose planners with maximum entropy inverse reinforcement learning. We evaluate our approach based on the expected value difference between learned and demonstrated policies. Furthermore, we compare the similarity of human driven trajectories with optimal policies of our planner under learned and expert-tuned reward functions. Our experiments show that we are able to learn reward functions exceeding the level of manual expert tuning without prior domain knowledge. |
| Tasks | Motion Planning |
| Published | 2019-05-01 |
| URL | http://arxiv.org/abs/1905.00229v1 |
| http://arxiv.org/pdf/1905.00229v1.pdf | |
| PWC | https://paperswithcode.com/paper/driving-with-style-inverse-reinforcement |
| Repo | |
| Framework | |
Open Domain Event Extraction Using Neural Latent Variable Models
| Title | Open Domain Event Extraction Using Neural Latent Variable Models |
| Authors | Xiao Liu, Heyan Huang, Yue Zhang |
| Abstract | We consider open domain event extraction, the task of extracting unconstraint types of events from news clusters. A novel latent variable neural model is constructed, which is scalable to very large corpus. A dataset is collected and manually annotated, with task-specific evaluation metrics being designed. Results show that the proposed unsupervised model gives better performance compared to the state-of-the-art method for event schema induction. |
| Tasks | Latent Variable Models |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.06947v1 |
| https://arxiv.org/pdf/1906.06947v1.pdf | |
| PWC | https://paperswithcode.com/paper/open-domain-event-extraction-using-neural |
| Repo | |
| Framework | |
Unbiased Smoothing using Particle Independent Metropolis-Hastings
| Title | Unbiased Smoothing using Particle Independent Metropolis-Hastings |
| Authors | Lawrence Middleton, George Deligiannidis, Arnaud Doucet, Pierre E. Jacob |
| Abstract | We consider the approximation of expectations with respect to the distribution of a latent Markov process given noisy measurements. This is known as the smoothing problem and is often approached with particle and Markov chain Monte Carlo (MCMC) methods. These methods provide consistent but biased estimators when run for a finite time. We propose a simple way of coupling two MCMC chains built using Particle Independent Metropolis-Hastings (PIMH) to produce unbiased smoothing estimators. Unbiased estimators are appealing in the context of parallel computing, and facilitate the construction of confidence intervals. The proposed scheme only requires access to off-the-shelf Particle Filters (PF) and is thus easier to implement than recently proposed unbiased smoothers. The approach is demonstrated on a L'evy-driven stochastic volatility model and a stochastic kinetic model. |
| Tasks | |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01781v1 |
| http://arxiv.org/pdf/1902.01781v1.pdf | |
| PWC | https://paperswithcode.com/paper/unbiased-smoothing-using-particle-independent |
| Repo | |
| Framework | |
Deep, spatially coherent Inverse Sensor Models with Uncertainty Incorporation using the evidential Framework
| Title | Deep, spatially coherent Inverse Sensor Models with Uncertainty Incorporation using the evidential Framework |
| Authors | Daniel Bauer, Lars Kuhnert, Lutz Eckstein |
| Abstract | To perform high speed tasks, sensors of autonomous cars have to provide as much information in as few time steps as possible. However, radars, one of the sensor modalities autonomous cars heavily rely on, often only provide sparse, noisy detections. These have to be accumulated over time to reach a high enough confidence about the static parts of the environment. For radars, the state is typically estimated by accumulating inverse detection models (IDMs). We employ the recently proposed evidential convolutional neural networks which, in contrast to IDMs, compute dense, spatially coherent inference of the environment state. Moreover, these networks are able to incorporate sensor noise in a principled way which we further extend to also incorporate model uncertainty. We present experimental results that show This makes it possible to obtain a denser environment perception in fewer time steps. |
| Tasks | |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1904.00842v1 |
| http://arxiv.org/pdf/1904.00842v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-spatially-coherent-inverse-sensor-models |
| Repo | |
| Framework | |
Robust Semantic Segmentation By Dense Fusion Network On Blurred VHR Remote Sensing Images
| Title | Robust Semantic Segmentation By Dense Fusion Network On Blurred VHR Remote Sensing Images |
| Authors | Yi Peng, Shihao Sun, Yining Pan, Ruirui Li |
| Abstract | Robust semantic segmentation of VHR remote sensing images from UAV sensors is critical for earth observation, land use, land cover or mapping applications. Several factors such as shadows, weather disruption and camera shakes making this problem highly challenging, especially only using RGB images. In this paper, we propose the use of multi-modality data including NIR, RGB and DSM to increase robustness of segmentation in blurred or partially damaged VHR remote sensing images. By proposing a cascaded dense encoder-decoder network and the SELayer based fusion and assembling techniques, the proposed RobustDenseNet achieves steady performance when the image quality is decreasing, compared with the state-of-the-art semantic segmentation model. |
| Tasks | Semantic Segmentation |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.02702v1 |
| http://arxiv.org/pdf/1903.02702v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-semantic-segmentation-by-dense-fusion |
| Repo | |
| Framework | |
Anytime Integrated Task and Motion Policies for Stochastic Environments
| Title | Anytime Integrated Task and Motion Policies for Stochastic Environments |
| Authors | Naman Shah, Kislay Kumar, Pranav Kamojjhala, Deepak Kala Vasudevan, Siddharth Srivastava |
| Abstract | In order to solve complex, long-horizon tasks, intelligent robots need to be able to carry out high-level, abstract planning and reasoning in conjunction with motion planning. However, abstract models are typically lossy and plans or policies computed using them are often unexecutable in practice. These problems are aggravated in more realistic situations with stochastic dynamics, where the robot needs to reason about, and plan for multiple possible contingencies. We present a new approach for integrated task and motion planning in stochastic settings. In contrast to prior work in this direction, we show that our approach can effectively compute integrated task and motion policies with branching structure encoding agent behaviors for various possible contingencies. We prove that our algorithm is probabilistically complete and can compute feasible solution policies in an anytime fashion so that the probability of encountering an unresolved contingency decreases over time. Empirical results on a set of challenging problems show the utility and scope of our methods. |
| Tasks | Motion Planning |
| Published | 2019-04-30 |
| URL | https://arxiv.org/abs/1904.13006v2 |
| https://arxiv.org/pdf/1904.13006v2.pdf | |
| PWC | https://paperswithcode.com/paper/anytime-integrated-task-and-motion-policies |
| Repo | |
| Framework | |
Incremental Learning of Discrete Planning Domains from Continuous Perceptions
| Title | Incremental Learning of Discrete Planning Domains from Continuous Perceptions |
| Authors | Luciano Serafini, Paolo Traverso |
| Abstract | We propose a framework for learning discrete deterministic planning domains. In this framework, an agent learns the domain by observing the action effects through continuous features that describe the state of the environment after the execution of each action. Besides, the agent learns its perception function, i.e., a probabilistic mapping between state variables and sensor data represented as a vector of continuous random variables called perception variables. We define an algorithm that updates the planning domain and the perception function by (i) introducing new states, either by extending the possible values of state variables, or by weakening their constraints; (ii) adapts the perception function to fit the observed data (iii) adapts the transition function on the basis of the executed actions and the effects observed via the perception function. The framework is able to deal with exogenous events that happen in the environment. |
| Tasks | |
| Published | 2019-03-14 |
| URL | http://arxiv.org/abs/1903.05937v2 |
| http://arxiv.org/pdf/1903.05937v2.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-learning-of-discrete-planning |
| Repo | |
| Framework | |
