Paper Group ANR 158
Optimistic bounds for multi-output prediction. Learning Object Placements For Relational Instructions by Hallucinating Scene Representations. Partial Gromov-Wasserstein with Applications on Positive-Unlabeled Learning. Deontological Ethics By Monotonicity Shape Constraints. Implementing Dynamic Answer Set Programming. A scheme for automatic differe …
Optimistic bounds for multi-output prediction
| Title | Optimistic bounds for multi-output prediction |
| Authors | Henry WJ Reeve, Ata Kaban |
| Abstract | We investigate the challenge of multi-output learning, where the goal is to learn a vector-valued function based on a supervised data set. This includes a range of important problems in Machine Learning including multi-target regression, multi-class classification and multi-label classification. We begin our analysis by introducing the self-bounding Lipschitz condition for multi-output loss functions, which interpolates continuously between a classical Lipschitz condition and a multi-dimensional analogue of a smoothness condition. We then show that the self-bounding Lipschitz condition gives rise to optimistic bounds for multi-output learning, which are minimax optimal up to logarithmic factors. The proof exploits local Rademacher complexity combined with a powerful minoration inequality due to Srebro, Sridharan and Tewari. As an application we derive a state-of-the-art generalization bound for multi-class gradient boosting. |
| Tasks | Multi-Label Classification |
| Published | 2020-02-22 |
| URL | https://arxiv.org/abs/2002.09769v1 |
| https://arxiv.org/pdf/2002.09769v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimistic-bounds-for-multi-output-prediction |
| Repo | |
| Framework | |
Learning Object Placements For Relational Instructions by Hallucinating Scene Representations
| Title | Learning Object Placements For Relational Instructions by Hallucinating Scene Representations |
| Authors | Oier Mees, Alp Emek, Johan Vertens, Wolfram Burgard |
| Abstract | Robots coexisting with humans in their environment and performing services for them need the ability to interact with them. One particular requirement for such robots is that they are able to understand spatial relations and can place objects in accordance with the spatial relations expressed by their user. In this work, we present a convolutional neural network for estimating pixelwise object placement probabilities for a set of spatial relations from a single input image. During training, our network receives the learning signal by classifying hallucinated high-level scene representations as an auxiliary task. Unlike previous approaches, our method does not require ground truth data for the pixelwise relational probabilities or 3D models of the objects, which significantly expands the applicability in practical applications. Our results obtained using real-world data and human-robot experiments demonstrate the effectiveness of our method in reasoning about the best way to place objects to reproduce a spatial relation. Videos of our experiments can be found at https://youtu.be/zaZkHTWFMKM |
| Tasks | |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2001.08481v2 |
| https://arxiv.org/pdf/2001.08481v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-object-placements-for-relational |
| Repo | |
| Framework | |
Partial Gromov-Wasserstein with Applications on Positive-Unlabeled Learning
| Title | Partial Gromov-Wasserstein with Applications on Positive-Unlabeled Learning |
| Authors | Laetitia Chapel, Mokhtar Z. Alaya, Gilles Gasso |
| Abstract | Optimal Transport (OT) framework allows defining similarity between probability distributions and provides metrics such as the Wasserstein and Gromov-Wasserstein discrepancies. Classical OT problem seeks a transportation map that preserves the total mass, requiring the mass of the source and target distributions to be the same. This may be too restrictive in certain applications such as color or shape matching, since the distributions may have arbitrary masses or that only a fraction of the total mass has to be transported. Several algorithms have been devised for computing unbalanced Wasserstein metrics but when it comes with the Gromov-Wasserstein problem, no partial formulation is available yet. This precludes from working with distributions that do not lie in the same metric space or when invariance to rotation or translation is needed. In this paper, we address the partial Gromov-Wasserstein problem and propose an algorithm to solve it. We showcase the new formulation in a positive-unlabeled (PU) learning application. To the best of our knowledge, this is the first application of optimal transport in this context and we first highlight that partial Wasserstein-based metrics prove effective in usual PU learning settings. We then demonstrate that partial Gromov-Wasserstein metrics is efficient in scenario where point clouds come from different domains or have different features. |
| Tasks | |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08276v1 |
| https://arxiv.org/pdf/2002.08276v1.pdf | |
| PWC | https://paperswithcode.com/paper/partial-gromov-wasserstein-with-applications |
| Repo | |
| Framework | |
Deontological Ethics By Monotonicity Shape Constraints
| Title | Deontological Ethics By Monotonicity Shape Constraints |
| Authors | Serena Wang, Maya Gupta |
| Abstract | We demonstrate how easy it is for modern machine-learned systems to violate common deontological ethical principles and social norms such as “favor the less fortunate,” and “do not penalize good attributes.” We propose that in some cases such ethical principles can be incorporated into a machine-learned model by adding shape constraints that constrain the model to respond only positively to relevant inputs. We analyze the relationship between these deontological constraints that act on individuals and the consequentialist group-based fairness goals of one-sided statistical parity and equal opportunity. This strategy works with sensitive attributes that are Boolean or real-valued such as income and age, and can help produce more responsible and trustworthy AI. |
| Tasks | |
| Published | 2020-01-31 |
| URL | https://arxiv.org/abs/2001.11990v2 |
| https://arxiv.org/pdf/2001.11990v2.pdf | |
| PWC | https://paperswithcode.com/paper/deontological-ethics-by-monotonicity-shape |
| Repo | |
| Framework | |
Implementing Dynamic Answer Set Programming
| Title | Implementing Dynamic Answer Set Programming |
| Authors | Pedro Cabalar, Martín Diéguez, Torsten Schaub, François Laferrière |
| Abstract | We introduce an implementation of an extension of Answer Set Programming (ASP) with language constructs from dynamic (and temporal) logic that provides an expressive computational framework for modeling dynamic applications. Starting from logical foundations, provided by dynamic and temporal equilibrium logics over finite linear traces, we develop a translation of dynamic formulas into temporal logic programs. This provides us with a normal form result establishing the strong equivalence of formulas in different logics. Our translation relies on the introduction of auxiliary atoms to guarantee polynomial space complexity and to provide an embedding that is doomed to be impossible over the same language. Finally, the reduction of dynamic formulas to temporal logic programs allows us to extend ASP with both approaches in a uniform way and to implement both extensions via temporal ASP solvers such as telingo |
| Tasks | |
| Published | 2020-02-17 |
| URL | https://arxiv.org/abs/2002.06916v2 |
| https://arxiv.org/pdf/2002.06916v2.pdf | |
| PWC | https://paperswithcode.com/paper/implementing-dynamic-answer-set-programming |
| Repo | |
| Framework | |
A scheme for automatic differentiation of complex loss functions
| Title | A scheme for automatic differentiation of complex loss functions |
| Authors | Chu Guo, Dario Poletti |
| Abstract | For a real function, automatic differentiation is such a standard algorithm used to efficiently compute its gradient, that it is integrated in various neural network frameworks. However, despite the recent advances in using complex functions in machine learning and the well-established usefulness of automatic differentiation, the support of automatic differentiation for complex functions is not as well-established and widespread as for real functions. In this work we propose an efficient and seamless scheme to implement automatic differentiation for complex functions, which is a compatible generalization of the current scheme for real functions. This scheme can significantly simplify the implementation of neural networks which use complex numbers. |
| Tasks | |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.04295v1 |
| https://arxiv.org/pdf/2003.04295v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-scheme-for-automatic-differentiation-of |
| Repo | |
| Framework | |
SurvLIME: A method for explaining machine learning survival models
| Title | SurvLIME: A method for explaining machine learning survival models |
| Authors | Maxim S. Kovalev, Lev V. Utkin, Ernest M. Kasimov |
| Abstract | A new method called SurvLIME for explaining machine learning survival models is proposed. It can be viewed as an extension or modification of the well-known method LIME. The main idea behind the proposed method is to apply the Cox proportional hazards model to approximate the survival model at the local area around a test example. The Cox model is used because it considers a linear combination of the example covariates such that coefficients of the covariates can be regarded as quantitative impacts on the prediction. Another idea is to approximate cumulative hazard functions of the explained model and the Cox model by using a set of perturbed points in a local area around the point of interest. The method is reduced to solving an unconstrained convex optimization problem. A lot of numerical experiments demonstrate the SurvLIME efficiency. |
| Tasks | |
| Published | 2020-03-18 |
| URL | https://arxiv.org/abs/2003.08371v1 |
| https://arxiv.org/pdf/2003.08371v1.pdf | |
| PWC | https://paperswithcode.com/paper/survlime-a-method-for-explaining-machine |
| Repo | |
| Framework | |
Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning
| Title | Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning |
| Authors | Yiyan Chen, Li Tao, Xueting Wang, Toshihiko Yamasaki |
| Abstract | Conventional video summarization approaches based on reinforcement learning have the problem that the reward can only be received after the whole summary is generated. Such kind of reward is sparse and it makes reinforcement learning hard to converge. Another problem is that labelling each frame is tedious and costly, which usually prohibits the construction of large-scale datasets. To solve these problems, we propose a weakly supervised hierarchical reinforcement learning framework, which decomposes the whole task into several subtasks to enhance the summarization quality. This framework consists of a manager network and a worker network. For each subtask, the manager is trained to set a subgoal only by a task-level binary label, which requires much fewer labels than conventional approaches. With the guide of the subgoal, the worker predicts the importance scores for video frames in the subtask by policy gradient according to both global reward and innovative defined sub-rewards to overcome the sparse problem. Experiments on two benchmark datasets show that our proposal has achieved the best performance, even better than supervised approaches. |
| Tasks | Hierarchical Reinforcement Learning, Supervised Video Summarization, Video Summarization |
| Published | 2020-01-12 |
| URL | https://arxiv.org/abs/2001.05864v2 |
| https://arxiv.org/pdf/2001.05864v2.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-video-summarization-by |
| Repo | |
| Framework | |
Communication Optimization Strategies for Distributed Deep Learning: A Survey
| Title | Communication Optimization Strategies for Distributed Deep Learning: A Survey |
| Authors | Shuo Ouyang, Dezun Dong, Yemao Xu, Liquan Xiao |
| Abstract | Recent trends in high-performance computing and deep learning lead to a proliferation of studies on large-scale deep neural network (DNN) training. However, the frequent communication requirements among computation nodes drastically slow down the overall training speed, which makes the bottleneck in distributed training, particularly in clusters with limited network bandwidth. To mitigate the drawbacks of distributed communication, researchers have proposed various optimization strategies. In this paper, we give a comprehensive survey of communication strategies from both algorithm and computer network perspectives. Algorithm optimizations focus on reducing the amount of communication in distributed training, while network optimizations focus on speeding up the communication between distributed devices. At the algorithm level, we describe how to reduce the number of communication rounds and transmitted bits per round, besides we shed light on how to overlap computation and communication. At the network level, we discuss the effect caused by network infrastructures, including communication schemes, network protocols, and topology. Finally, we extrapolate potential challenges and research directions for communication acceleration in distributed DNN training. |
| Tasks | |
| Published | 2020-03-06 |
| URL | https://arxiv.org/abs/2003.03009v1 |
| https://arxiv.org/pdf/2003.03009v1.pdf | |
| PWC | https://paperswithcode.com/paper/communication-optimization-strategies-for |
| Repo | |
| Framework | |
Finding manoeuvre motifs in vehicle telematics
| Title | Finding manoeuvre motifs in vehicle telematics |
| Authors | Maria Inês Silva, Roberto Henriques |
| Abstract | Driving behaviour has a great impact on road safety. A popular way of analysing driving behaviour is to move the focus to the manoeuvres as they give useful information about the driver who is performing them. In this paper, we investigate a new way of identifying manoeuvres from vehicle telematics data, through motif detection in time-series. We implement a modified version of the Extended Motif Discovery (EMD) algorithm, a classical variable-length motif detection algorithm for time-series and we applied it to the UAH-DriveSet, a publicly available naturalistic driving dataset. After a systematic exploration of the extracted motifs, we were able to conclude that the EMD algorithm was not only capable of extracting simple manoeuvres such as accelerations, brakes and curves, but also more complex manoeuvres, such as lane changes and overtaking manoeuvres, which validates motif discovery as a worthwhile line for future research. |
| Tasks | Time Series |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.04127v1 |
| https://arxiv.org/pdf/2002.04127v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-manoeuvre-motifs-in-vehicle |
| Repo | |
| Framework | |
A Prototype of Serverless Lucene
| Title | A Prototype of Serverless Lucene |
| Authors | Jimmy Lin |
| Abstract | This paper describes a working prototype that adapts Lucene, the world’s most popular and most widely deployed open-source search library, to operate within a serverless environment in the cloud. Although the serverless search concept is not new, this work represents a substantial improvement over a previous implementation in eliminating most custom code and in enabling interactive search. While there remain limitations to the design, it nevertheless challenges conventional thinking about search architectures for particular operating points. |
| Tasks | |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01447v1 |
| https://arxiv.org/pdf/2002.01447v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-prototype-of-serverless-lucene |
| Repo | |
| Framework | |
FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MEC
| Title | FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MEC |
| Authors | Rongfei Zeng, Shixun Zhang, Jiaqi Wang, Xiaowen Chu |
| Abstract | Promising federated learning coupled with Mobile Edge Computing (MEC) is considered as one of the most promising solutions to the AI-driven service provision. Plenty of studies focus on federated learning from the performance and security aspects, but they neglect the incentive mechanism. In MEC, edge nodes would not like to voluntarily participate in learning, and they differ in the provision of multi-dimensional resources, both of which might deteriorate the performance of federated learning. Also, lightweight schemes appeal to edge nodes in MEC. These features require the incentive mechanism to be well designed for MEC. In this paper, we present an incentive mechanism FMore with multi-dimensional procurement auction of K winners. Our proposal FMore not only is lightweight and incentive compatible, but also encourages more high-quality edge nodes with low cost to participate in learning and eventually improve the performance of federated learning. We also present theoretical results of Nash equilibrium strategy to edge nodes and employ the expected utility theory to provide guidance to the aggregator. Both extensive simulations and real-world experiments demonstrate that the proposed scheme can effectively reduce the training rounds and drastically improve the model accuracy for challenging AI tasks. |
| Tasks | |
| Published | 2020-02-22 |
| URL | https://arxiv.org/abs/2002.09699v1 |
| https://arxiv.org/pdf/2002.09699v1.pdf | |
| PWC | https://paperswithcode.com/paper/fmore-an-incentive-scheme-of-multi |
| Repo | |
| Framework | |
DeFraudNet:End2End Fingerprint Spoof Detection using Patch Level Attention
| Title | DeFraudNet:End2End Fingerprint Spoof Detection using Patch Level Attention |
| Authors | B. V. S Anusha, Sayan Banerjee, Subhasis Chaudhuri |
| Abstract | In recent years, fingerprint recognition systems have made remarkable advancements in the field of biometric security as it plays an important role in personal, national and global security. In spite of all these notable advancements, the fingerprint recognition technology is still susceptible to spoof attacks which can significantly jeopardize the user security. The cross sensor and cross material spoof detection still pose a challenge with a myriad of spoof materials emerging every day, compromising sensor interoperability and robustness. This paper proposes a novel method for fingerprint spoof detection using both global and local fingerprint feature descriptors. These descriptors are extracted using DenseNet which significantly improves cross-sensor, cross-material and cross-dataset performance. A novel patch attention network is used for finding the most discriminative patches and also for network fusion. We evaluate our method on four publicly available datasets:LivDet 2011, 2013, 2015 and 2017. A set of comprehensive experiments are carried out to evaluate cross-sensor, cross-material and cross-dataset performance over these datasets. The proposed approach achieves an average accuracy of 99.52%, 99.16% and 99.72% on LivDet 2017,2015 and 2011 respectively outperforming the current state-of-the-art results by 3% and 4% for LivDet 2015 and 2011 respectively. |
| Tasks | |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08214v1 |
| https://arxiv.org/pdf/2002.08214v1.pdf | |
| PWC | https://paperswithcode.com/paper/defraudnetend2end-fingerprint-spoof-detection |
| Repo | |
| Framework | |
Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation
| Title | Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation |
| Authors | Dengsheng Chen, Jun Li, Zheng Wang, Kai Xu |
| Abstract | We present a novel approach to category-level 6D object pose and size estimation. To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object category. In particular, CASS is modeled as the latent space of a deep generative model of canonical 3D shapes with normalized pose. We train a variational auto-encoder (VAE) for generating 3D point clouds in the canonical space from an RGBD image. The VAE is trained in a cross-category fashion, exploiting the publicly available large 3D shape repositories. Since the 3D point cloud is generated in normalized pose (with actual size), the encoder of the VAE learns view-factorized RGBD embedding. It maps an RGBD image in arbitrary view into a pose-independent 3D shape representation. Object pose is then estimated via contrasting it with a pose-dependent feature of the input RGBD extracted with a separate deep neural networks. We integrate the learning of CASS and pose and size estimation into an end-to-end trainable network, achieving the state-of-the-art performance. |
| Tasks | 3D Shape Representation, Generating 3D Point Clouds |
| Published | 2020-01-25 |
| URL | https://arxiv.org/abs/2001.09322v2 |
| https://arxiv.org/pdf/2001.09322v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-canonical-shape-space-for-category |
| Repo | |
| Framework | |
I-ViSE: Interactive Video Surveillance as an Edge Service using Unsupervised Feature Queries
| Title | I-ViSE: Interactive Video Surveillance as an Edge Service using Unsupervised Feature Queries |
| Authors | Seyed Yahya Nikouei, Yu Chen, Alexander Aved, Erik Blasch |
| Abstract | Situation AWareness (SAW) is essential for many mission critical applications. However, SAW is very challenging when trying to immediately identify objects of interest or zoom in on suspicious activities from thousands of video frames. This work aims at developing a queryable system to instantly select interesting content. While face recognition technology is mature, in many scenarios like public safety monitoring, the features of objects of interest may be much more complicated than face features. In addition, human operators may not be always able to provide a descriptive, simple, and accurate query. Actually, it is more often that there are only rough, general descriptions of certain suspicious objects or accidents. This paper proposes an Interactive Video Surveillance as an Edge service (I-ViSE) based on unsupervised feature queries. Adopting unsupervised methods that do not reveal any private information, the I-ViSE scheme utilizes general features of a human body and color of clothes. An I-ViSE prototype is built following the edge-fog computing paradigm and the experimental results verified the I-ViSE scheme meets the design goal of scene recognition in less than two seconds. |
| Tasks | Face Recognition, Scene Recognition |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.04169v1 |
| https://arxiv.org/pdf/2003.04169v1.pdf | |
| PWC | https://paperswithcode.com/paper/i-vise-interactive-video-surveillance-as-an |
| Repo | |
| Framework | |
