Paper Group ANR 106
Knowledge Reconciliation of $n$-ary Relations. Cross Lingual Cross Corpus Speech Emotion Recognition. Learning Topometric Semantic Maps from Occupancy Grids. Logistic-Regression with peer-group effects via inference in higher order Ising models. Engineering AI Systems: A Research Agenda. Signature in Counterparts, a Formal Treatment. End-to-End Lea …
Knowledge Reconciliation of $n$-ary Relations
| Title | Knowledge Reconciliation of $n$-ary Relations |
| Authors | Pierre Monnin, Miguel Couceiro, Amedeo Napoli, Adrien Coulet |
| Abstract | In the expanding Semantic Web, an increasing number of sources of data and knowledge are accessible by human and software agents. Sources may differ in granularity or completeness, and thus be complementary. Consequently, unlocking the full potential of the available knowledge requires combining them. To this aim, we define the task of knowledge reconciliation, which consists in identifying, within and across sources, equivalent, more specific, or similar units. This task can be challenging since knowledge units are heterogeneously represented in sources (e.g., in terms of vocabularies). In this paper, we propose a rule-based methodology for the reconciliation of $n$-ary relations. To alleviate the heterogeneity in representation, we rely on domain knowledge expressed by ontologies. We tested our method on the biomedical domain of pharmacogenomics by reconciling 50,435 $n$-ary relations from four different real-world sources, which highlighted noteworthy agreements and discrepancies within and across sources. |
| Tasks | |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08103v1 |
| https://arxiv.org/pdf/2002.08103v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-reconciliation-of-n-ary-relations |
| Repo | |
| Framework | |
Cross Lingual Cross Corpus Speech Emotion Recognition
| Title | Cross Lingual Cross Corpus Speech Emotion Recognition |
| Authors | Shivali Goel, Homayoon Beigi |
| Abstract | The majority of existing speech emotion recognition models are trained and evaluated on a single corpus and a single language setting. These systems do not perform as well when applied in a cross-corpus and cross-language scenario. This paper presents results for speech emotion recognition for 4 languages in both single corpus and cross corpus setting. Additionally, since multi-task learning (MTL) with gender, naturalness and arousal as auxiliary tasks has shown to enhance the generalisation capabilities of the emotion models, this paper introduces language ID as another auxiliary task in MTL framework to explore the role of spoken language on emotion recognition which has not been studied yet. |
| Tasks | Emotion Recognition, Multi-Task Learning, Speech Emotion Recognition |
| Published | 2020-03-18 |
| URL | https://arxiv.org/abs/2003.07996v1 |
| https://arxiv.org/pdf/2003.07996v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-lingual-cross-corpus-speech-emotion |
| Repo | |
| Framework | |
Learning Topometric Semantic Maps from Occupancy Grids
| Title | Learning Topometric Semantic Maps from Occupancy Grids |
| Authors | Markus Hiller, Chen Qiu, Florian Particke, Christian Hofmann, Jörn Thielecke |
| Abstract | Today’s mobile robots are expected to operate in complex environments they share with humans. To allow intuitive human-robot collaboration, robots require a human-like understanding of their surroundings in terms of semantically classified instances. In this paper, we propose a new approach for deriving such instance-based semantic maps purely from occupancy grids. We employ a combination of deep learning techniques to detect, segment and extract door hypotheses from a random-sized map. The extraction is followed by a post-processing chain to further increase the accuracy of our approach, as well as place categorization for the three classes room, door and corridor. All detected and classified entities are described as instances specified in a common coordinate system, while a topological map is derived to capture their spatial links. To train our two neural networks used for detection and map segmentation, we contribute a simulator that automatically creates and annotates the required training data. We further provide insight into which features are learned to detect doorways, and how the simulated training data can be augmented to train networks for the direct application on real-world grid maps. We evaluate our approach on several publicly available real-world data sets. Even though the used networks are solely trained on simulated data, our approach demonstrates high robustness and effectiveness in various real-world indoor environments. |
| Tasks | |
| Published | 2020-01-10 |
| URL | https://arxiv.org/abs/2001.03676v1 |
| https://arxiv.org/pdf/2001.03676v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-topometric-semantic-maps-from |
| Repo | |
| Framework | |
Logistic-Regression with peer-group effects via inference in higher order Ising models
| Title | Logistic-Regression with peer-group effects via inference in higher order Ising models |
| Authors | Constantinos Daskalakis, Nishanth Dikkala, Ioannis Panageas |
| Abstract | Spin glass models, such as the Sherrington-Kirkpatrick, Hopfield and Ising models, are all well-studied members of the exponential family of discrete distributions, and have been influential in a number of application domains where they are used to model correlation phenomena on networks. Conventionally these models have quadratic sufficient statistics and consequently capture correlations arising from pairwise interactions. In this work we study extensions of these to models with higher-order sufficient statistics, modeling behavior on a social network with peer-group effects. In particular, we model binary outcomes on a network as a higher-order spin glass, where the behavior of an individual depends on a linear function of their own vector of covariates and some polynomial function of the behavior of others, capturing peer-group effects. Using a {\em single}, high-dimensional sample from such model our goal is to recover the coefficients of the linear function as well as the strength of the peer-group effects. The heart of our result is a novel approach for showing strong concavity of the log pseudo-likelihood of the model, implying statistical error rate of $\sqrt{d/n}$ for the Maximum Pseudo-Likelihood Estimator (MPLE), where $d$ is the dimensionality of the covariate vectors and $n$ is the size of the network (number of nodes). Our model generalizes vanilla logistic regression as well as the peer-effect models studied in recent works, and our results extend these results to accommodate higher-order interactions. |
| Tasks | |
| Published | 2020-03-18 |
| URL | https://arxiv.org/abs/2003.08259v1 |
| https://arxiv.org/pdf/2003.08259v1.pdf | |
| PWC | https://paperswithcode.com/paper/logistic-regression-with-peer-group-effects |
| Repo | |
| Framework | |
Engineering AI Systems: A Research Agenda
| Title | Engineering AI Systems: A Research Agenda |
| Authors | Jan Bosch, Ivica Crnkovic, Helena Holmström Olsson |
| Abstract | Deploying machine-, and in particular deep-learning, (ML/DL) solutions in industry-strength, production quality contexts proves to challenging. This requires a structured engineering approach to constructing and evolving systems that contain ML/DL components. In this paper, we provide a conceptualization of the typical evolution patterns that companies experience when employing ML/DL well as a framework for integrating ML/DL components in systems consisting of multiple types of components. In addition, we provide an overview of the engineering challenges surrounding AI/ML/DL solutions and, based on that, we provide a research agenda and overview of open items that need to be addressed by the research community at large. |
| Tasks | |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.07522v1 |
| https://arxiv.org/pdf/2001.07522v1.pdf | |
| PWC | https://paperswithcode.com/paper/engineering-ai-systems-a-research-agenda |
| Repo | |
| Framework | |
Signature in Counterparts, a Formal Treatment
| Title | Signature in Counterparts, a Formal Treatment |
| Authors | Ron van der Meyden |
| Abstract | “Signature in counterparts” is a legal process that permits a contract between two or more parties to be brought into force by having the parties independently (possibly, remotely) sign different copies of the contract, rather than placing their signatures on a common copy at a physical meeting. The paper develops a logical understanding of this process, developing a number of axioms that can be used to justify the validity of a contract from the assumption that separate copies have been signed. It is argued that a satisfactory account benefits from a logic with syntactic self-reference. The axioms used are supported by a formal semantics, and a number of further properties of this semantics are investigated. In particular, it is shown that the semantics implies that when a contract is valid, the parties do not just agree, but are in mutual agreement (a common-knowledge-like notion) about the validity of the contract. |
| Tasks | |
| Published | 2020-02-23 |
| URL | https://arxiv.org/abs/2002.09827v1 |
| https://arxiv.org/pdf/2002.09827v1.pdf | |
| PWC | https://paperswithcode.com/paper/signature-in-counterparts-a-formal-treatment |
| Repo | |
| Framework | |
End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
| Title | End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds |
| Authors | Lei Li, Siyu Zhu, Hongbo Fu, Ping Tan, Chiew-Lan Tai |
| Abstract | In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively. |
| Tasks | |
| Published | 2020-03-12 |
| URL | https://arxiv.org/abs/2003.05855v2 |
| https://arxiv.org/pdf/2003.05855v2.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-learning-local-multi-view |
| Repo | |
| Framework | |
Differentially Private Deep Learning with Smooth Sensitivity
| Title | Differentially Private Deep Learning with Smooth Sensitivity |
| Authors | Lichao Sun, Yingbo Zhou, Philip S. Yu, Caiming Xiong |
| Abstract | Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One approach to study these concerns is through the lens of differential privacy. In this framework, privacy guarantees are generally obtained by perturbing models in such a way that specifics of data used to train the model are made ambiguous. A particular instance of this approach is through a “teacher-student” framework, wherein the teacher, who owns the sensitive data, provides the student with useful, but noisy, information, hopefully allowing the student model to perform well on a given task without access to particular features of the sensitive data. Because stronger privacy guarantees generally involve more significant perturbation on the part of the teacher, deploying existing frameworks fundamentally involves a trade-off between student’s performance and privacy guarantee. One of the most important techniques used in previous works involves an ensemble of teacher models, which return information to a student based on a noisy voting procedure. In this work, we propose a novel voting mechanism with smooth sensitivity, which we call Immutable Noisy ArgMax, that, under certain conditions, can bear very large random noising from the teacher without affecting the useful information transferred to the student. Compared with previous work, our approach improves over the state-of-the-art methods on all measures, and scale to larger tasks with both better performance and stronger privacy ($\epsilon \approx 0$). This new proposed framework can be applied with any machine learning models, and provides an appealing solution for tasks that requires training on a large amount of data. |
| Tasks | |
| Published | 2020-03-01 |
| URL | https://arxiv.org/abs/2003.00505v1 |
| https://arxiv.org/pdf/2003.00505v1.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-deep-learning-with |
| Repo | |
| Framework | |
Progress Extrapolating Algorithmic Learning to Arbitrary Sequence Lengths
| Title | Progress Extrapolating Algorithmic Learning to Arbitrary Sequence Lengths |
| Authors | Andreas Robinson |
| Abstract | Recent neural network models for algorithmic tasks have led to significant improvements in extrapolation to sequences much longer than training, but it remains an outstanding problem that the performance still degrades for very long or adversarial sequences. We present alternative architectures and loss-terms to address these issues, and our testing of these approaches has not detected any remaining extrapolation errors within memory constraints. We focus on linear time algorithmic tasks including copy, parentheses parsing, and binary addition. First, activation binning was used to discretize the trained network in order to avoid computational drift from continuous operations, and a binning-based digital loss term was added to encourage discretizable representations. In addition, a localized differentiable memory (LDM) architecture, in contrast to distributed memory access, addressed remaining extrapolation errors and avoided unbounded growth of internal computational states. Previous work has found that algorithmic extrapolation issues can also be alleviated with approaches relying on program traces, but the current effort does not rely on such traces. |
| Tasks | |
| Published | 2020-03-18 |
| URL | https://arxiv.org/abs/2003.08494v2 |
| https://arxiv.org/pdf/2003.08494v2.pdf | |
| PWC | https://paperswithcode.com/paper/progress-extrapolating-algorithmic-learning |
| Repo | |
| Framework | |
ML4Chem: A Machine Learning Package for Chemistry and Materials Science
| Title | ML4Chem: A Machine Learning Package for Chemistry and Materials Science |
| Authors | Muammar El Khatib, Wibe A de Jong |
| Abstract | ML4Chem is an open-source machine learning library for chemistry and materials science. It provides an extendable platform to develop and deploy machine learning models and pipelines and is targeted to the non-expert and expert users. ML4Chem follows user-experience design and offers the needed tools to go from data preparation to inference. Here we introduce its atomistic module for the implementation, deployment, and reproducibility of atom-centered models. This module is composed of six core building blocks: data, featurization, models, model optimization, inference, and visualization. We present their functionality and easiness of use with demonstrations utilizing neural networks and kernel ridge regression algorithms. |
| Tasks | |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.13388v1 |
| https://arxiv.org/pdf/2003.13388v1.pdf | |
| PWC | https://paperswithcode.com/paper/ml4chem-a-machine-learning-package-for |
| Repo | |
| Framework | |
Learning to Move with Affordance Maps
| Title | Learning to Move with Affordance Maps |
| Authors | William Qi, Ravi Teja Mullapudi, Saurabh Gupta, Deva Ramanan |
| Abstract | The ability to autonomously explore and navigate a physical space is a fundamental requirement for virtually any mobile autonomous agent, from household robotic vacuums to autonomous vehicles. Traditional SLAM-based approaches for exploration and navigation largely focus on leveraging scene geometry, but fail to model dynamic objects (such as other agents) or semantic constraints (such as wet floors or doorways). Learning-based RL agents are an attractive alternative because they can incorporate both semantic and geometric information, but are notoriously sample inefficient, difficult to generalize to novel settings, and are difficult to interpret. In this paper, we combine the best of both worlds with a modular approach that learns a spatial representation of a scene that is trained to be effective when coupled with traditional geometric planners. Specifically, we design an agent that learns to predict a spatial affordance map that elucidates what parts of a scene are navigable through active self-supervised experience gathering. In contrast to most simulation environments that assume a static world, we evaluate our approach in the VizDoom simulator, using large-scale randomly-generated maps containing a variety of dynamic actors and hazards. We show that learned affordance maps can be used to augment traditional approaches for both exploration and navigation, providing significant improvements in performance. |
| Tasks | Autonomous Vehicles |
| Published | 2020-01-08 |
| URL | https://arxiv.org/abs/2001.02364v2 |
| https://arxiv.org/pdf/2001.02364v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-move-with-affordance-maps-1 |
| Repo | |
| Framework | |
On the Mutual Information between Source and Filter Contributions for Voice Pathology Detection
| Title | On the Mutual Information between Source and Filter Contributions for Voice Pathology Detection |
| Authors | Thomas Drugman, Thomas Dubuisson, Thierry Dutoit |
| Abstract | This paper addresses the problem of automatic detection of voice pathologies directly from the speech signal. For this, we investigate the use of the glottal source estimation as a means to detect voice disorders. Three sets of features are proposed, depending on whether they are related to the speech or the glottal signal, or to prosody. The relevancy of these features is assessed through mutual information-based measures. This allows an intuitive interpretation in terms of discrimation power and redundancy between the features, independently of any subsequent classifier. It is discussed which characteristics are interestingly informative or complementary for detecting voice pathologies. |
| Tasks | |
| Published | 2020-01-02 |
| URL | https://arxiv.org/abs/2001.00583v1 |
| https://arxiv.org/pdf/2001.00583v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-mutual-information-between-source-and |
| Repo | |
| Framework | |
End-to-End Vision-Based Adaptive Cruise Control (ACC) Using Deep Reinforcement Learning
| Title | End-to-End Vision-Based Adaptive Cruise Control (ACC) Using Deep Reinforcement Learning |
| Authors | Zhensong Wei, Yu Jiang, Xishun Liao, Xuewei Qi, Ziran Wang, Guoyuan Wu, Peng Hao, Matthew Barth |
| Abstract | This paper presented a deep reinforcement learning method named Double Deep Q-networks to design an end-to-end vision-based adaptive cruise control (ACC) system. A simulation environment of a highway scene was set up in Unity, which is a game engine that provided both physical models of vehicles and feature data for training and testing. Well-designed reward functions associated with the following distance and throttle/brake force were implemented in the reinforcement learning model for both internal combustion engine (ICE) vehicles and electric vehicles (EV) to perform adaptive cruise control. The gap statistics and total energy consumption are evaluated for different vehicle types to explore the relationship between reward functions and powertrain characteristics. Compared with the traditional radar-based ACC systems or human-in-the-loop simulation, the proposed vision-based ACC system can generate either a better gap regulated trajectory or a smoother speed trajectory depending on the preset reward function. The proposed system can be well adaptive to different speed trajectories of the preceding vehicle and operated in real-time. |
| Tasks | |
| Published | 2020-01-24 |
| URL | https://arxiv.org/abs/2001.09181v1 |
| https://arxiv.org/pdf/2001.09181v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-vision-based-adaptive-cruise |
| Repo | |
| Framework | |
Coarse-Grain Cluster Analysis of Tensors With Application to Climate Biome Identification
| Title | Coarse-Grain Cluster Analysis of Tensors With Application to Climate Biome Identification |
| Authors | Derek DeSantis, Phillip J. Wolfram, Katrina Bennett, Boian Alexandrov |
| Abstract | A tensor provides a concise way to codify the interdependence of complex data. Treating a tensor as a d-way array, each entry records the interaction between the different indices. Clustering provides a way to parse the complexity of the data into more readily understandable information. Clustering methods are heavily dependent on the algorithm of choice, as well as the chosen hyperparameters of the algorithm. However, their sensitivity to data scales is largely unknown. In this work, we apply the discrete wavelet transform to analyze the effects of coarse-graining on clustering tensor data. We are particularly interested in understanding how scale effects clustering of the Earth’s climate system. The discrete wavelet transform allows classification of the Earth’s climate across a multitude of spatial-temporal scales. The discrete wavelet transform is used to produce an ensemble of classification estimates, as opposed to a single classification. Using information theory, we discover a sub-collection of the ensemble that span the majority of the variance observed, allowing for efficient consensus clustering techniques that can be used to identify climate biomes. |
| Tasks | |
| Published | 2020-01-22 |
| URL | https://arxiv.org/abs/2001.07827v1 |
| https://arxiv.org/pdf/2001.07827v1.pdf | |
| PWC | https://paperswithcode.com/paper/coarse-grain-cluster-analysis-of-tensors-with |
| Repo | |
| Framework | |
Hoplite: Efficient Collective Communication for Task-Based Distributed Systems
| Title | Hoplite: Efficient Collective Communication for Task-Based Distributed Systems |
| Authors | Siyuan Zhuang, Zhuohan Li, Danyang Zhuo, Stephanie Wang, Eric Liang, Robert Nishihara, Philipp Moritz, Ion Stoica |
| Abstract | Collective communication systems such as MPI offer high performance group communication primitives at the cost of application flexibility. Today, an increasing number of distributed applications (e.g, reinforcement learning) require flexibility in expressing dynamic and asynchronous communication patterns. To accommodate these applications, task-based distributed computing frameworks (e.g., Ray, Dask, Hydro) have become popular as they allow applications to dynamically specify communication by invoking tasks, or functions, at runtime. This design makes efficient collective communication challenging because (1) the group of communicating processes is chosen at runtime, and (2) processes may not all be ready at the same time. We design and implement Hoplite, a communication layer for task-based distributed systems that achieves high performance collective communication without compromising application flexibility. The key idea of Hoplite is to use distributed protocols to compute a data transfer schedule on the fly. This enables the same optimizations used in traditional collective communication, but for applications that specify the communication incrementally. We show that Hoplite can achieve similar performance compared with a traditional collective communication library, MPICH. We port a popular distributed computing framework, Ray, on atop of Hoplite. We show that Hoplite can speed up asynchronous parameter server and distributed reinforcement learning workloads that are difficult to execute efficiently with traditional collective communication by up to 8.1x and 3.9x, respectively. |
| Tasks | |
| Published | 2020-02-13 |
| URL | https://arxiv.org/abs/2002.05814v1 |
| https://arxiv.org/pdf/2002.05814v1.pdf | |
| PWC | https://paperswithcode.com/paper/hoplite-efficient-collective-communication |
| Repo | |
| Framework | |
