April 3, 2020

3256 words 16 mins read

Paper Group ANR 78

Paper Group ANR 78

Understanding Contexts Inside Robot and Human Manipulation Tasks through a Vision-Language Model and Ontology System in a Video Stream. PDGM: a Neural Network Approach to Solve Path-Dependent Partial Differential Equations. Learning Fairness-aware Relational Structures. Leveraging Cross Feedback of User and Item Embeddings for Variational Autoencod …

Understanding Contexts Inside Robot and Human Manipulation Tasks through a Vision-Language Model and Ontology System in a Video Stream

Title Understanding Contexts Inside Robot and Human Manipulation Tasks through a Vision-Language Model and Ontology System in a Video Stream
Authors Chen Jiang, Masood Dehghan, Martin Jagersand
Abstract Manipulation tasks in daily life, such as pouring water, unfold intentionally under specialized manipulation contexts. Being able to process contextual knowledge in these Activities of Daily Living (ADLs) over time can help us understand manipulation intentions, which are essential for an intelligent robot to transition smoothly between various manipulation actions. In this paper, to model the intended concepts of manipulation, we present a vision dataset under a strictly constrained knowledge domain for both robot and human manipulations, where manipulation concepts and relations are stored by an ontology system in a taxonomic manner. Furthermore, we propose a scheme to generate a combination of visual attentions and an evolving knowledge graph filled with commonsense knowledge. Our scheme works with real-world camera streams and fuses an attention-based Vision-Language model with the ontology system. The experimental results demonstrate that the proposed scheme can successfully represent the evolution of an intended object manipulation procedure for both robots and humans. The proposed scheme allows the robot to mimic human-like intentional behaviors by watching real-time videos. We aim to develop this scheme further for real-world robot intelligence in Human-Robot Interaction.
Tasks Language Modelling
Published 2020-03-02
URL https://arxiv.org/abs/2003.01163v1
PDF https://arxiv.org/pdf/2003.01163v1.pdf
PWC https://paperswithcode.com/paper/understanding-contexts-inside-robot-and-human

PDGM: a Neural Network Approach to Solve Path-Dependent Partial Differential Equations

Title PDGM: a Neural Network Approach to Solve Path-Dependent Partial Differential Equations
Authors Yuri F. Saporito, Zhaoyu Zhang
Abstract In this paper we propose a generalization of the Deep Galerking Method (DGM) of \cite{dgm} to deal with Path-Dependent Partial Differential Equations (PPDEs). These equations firstly appeared in the seminal work of \cite{fito_dupire}, where the functional It^o calculus was developed to deal with path-dependent financial derivatives contracts. The method, which we call Path-Dependent DGM (PDGM), consists of using a combination of feed-forward and Long Short-Term Memory architectures to model the solution of the PPDE. We then analyze several numerical examples, many from the Financial Mathematics literature, that show the capabilities of the method under very different situations.
Published 2020-03-04
URL https://arxiv.org/abs/2003.02035v1
PDF https://arxiv.org/pdf/2003.02035v1.pdf
PWC https://paperswithcode.com/paper/pdgm-a-neural-network-approach-to-solve-path

Learning Fairness-aware Relational Structures

Title Learning Fairness-aware Relational Structures
Authors Yue Zhang, Arti Ramesh
Abstract The development of fair machine learning models that effectively avert bias and discrimination is an important problem that has garnered attention in recent years. The necessity of encoding complex relational dependencies among the features and variables for competent predictions require the development of fair, yet expressive relational models. In this work, we introduce Fair-A3SL, a fairness-aware structure learning algorithm for learning relational structures, which incorporates fairness measures while learning relational graphical model structures. Our approach is versatile in being able to encode a wide range of fairness metrics such as statistical parity difference, overestimation, equalized odds, and equal opportunity, including recently proposed relational fairness measures. While existing approaches employ the fairness measures on pre-determined model structures post prediction, Fair-A3SL directly learns the structure while optimizing for the fairness measures and hence is able to remove any structural bias in the model. We demonstrate the effectiveness of our learned model structures when compared with the state-of-the-art fairness models quantitatively and qualitatively on datasets representing three different modeling scenarios: i) a relational dataset, ii) a recidivism prediction dataset widely used in studying discrimination, and iii) a recommender systems dataset. Our results show that Fair-A3SL can learn fair, yet interpretable and expressive structures capable of making accurate predictions.
Tasks Recommendation Systems
Published 2020-02-21
URL https://arxiv.org/abs/2002.09471v1
PDF https://arxiv.org/pdf/2002.09471v1.pdf
PWC https://paperswithcode.com/paper/learning-fairness-aware-relational-structures

Leveraging Cross Feedback of User and Item Embeddings for Variational Autoencoder based Collaborative Filtering

Title Leveraging Cross Feedback of User and Item Embeddings for Variational Autoencoder based Collaborative Filtering
Authors Yuan Jin, He Zhao, Ming Liu, Lan Du, Yunfeng Li, Ruohua Xu, Longxiang Gao
Abstract Matrix factorization (MF) has been widely applied to collaborative filtering in recommendation systems. Its Bayesian variants can derive posterior distributions of user and item embeddings, and are more robust to sparse ratings. However, the Bayesian methods are restricted by their update rules for the posterior parameters due to the conjugacy of the priors and the likelihood. Neural networks can potentially address this issue by capturing complex mappings between the posterior parameters and the data. In this paper, we propose a variational auto-encoder based Bayesian MF framework. It leverages not only the data but also the information from the embeddings to approximate their joint posterior distribution. The approximation is an iterative procedure with cross feedback of user and item embeddings to the others’ encoders. More specifically, user embeddings sampled in the previous iteration, alongside their ratings, are fed back into the item-side encoders to compute the posterior parameters for the item embeddings in the current iteration, and vice versa. The decoder network then reconstructs the data using the MF with the currently re-sampled user and item embeddings. We show the effectiveness of our framework in terms of reconstruction errors across five real-world datasets. We also perform ablation studies to illustrate the importance of the cross feedback component of our framework in lowering the reconstruction errors and accelerating the convergence.
Tasks Recommendation Systems
Published 2020-02-21
URL https://arxiv.org/abs/2002.09145v1
PDF https://arxiv.org/pdf/2002.09145v1.pdf
PWC https://paperswithcode.com/paper/leveraging-cross-feedback-of-user-and-item

Deform-GAN:An Unsupervised Learning Model for Deformable Registration

Title Deform-GAN:An Unsupervised Learning Model for Deformable Registration
Authors Xiaoyue Zhang, Weijian Jian, Yu Chen, Shihting Yang
Abstract Deformable registration is one of the most challenging task in the field of medical image analysis, especially for the alignment between different sequences and modalities. In this paper, a non-rigid registration method is proposed for 3D medical images leveraging unsupervised learning. To the best of our knowledge, this is the first attempt to introduce gradient loss into deep-learning-based registration. The proposed gradient loss is robust across sequences and modals for large deformation. Besides, adversarial learning approach is used to transfer multi-modal similarity to mono-modal similarity and improve the precision. Neither ground-truth nor manual labeling is required during training. We evaluated our network on a 3D brain registration task comprehensively. The experiments demonstrate that the proposed method can cope with the data which has non-functional intensity relations, noise and blur. Our approach outperforms other methods especially in accuracy and speed.
Published 2020-02-26
URL https://arxiv.org/abs/2002.11430v1
PDF https://arxiv.org/pdf/2002.11430v1.pdf
PWC https://paperswithcode.com/paper/deform-ganan-unsupervised-learning-model-for

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

Title Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
Authors Wenqiang Lei, Xiangnan He, Yisong Miao, Qingyun Wu, Richang Hong, Min-Yen Kan, Tat-Seng Chua
Abstract Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models. A successful Conversational Recommender System (CRS) requires proper handling of interactions between conversation and recommendation. We argue that three fundamental problems need to be solved: 1) what questions to ask regarding item attributes, 2) when to recommend items, and 3) how to adapt to the users’ online feedback. To the best of our knowledge, there lacks a unified framework that addresses these problems. In this work, we fill this missing interaction framework gap by proposing a new CRS framework named Estimation-Action-Reflection, or EAR, which consists of three stages to better converse with users. (1) Estimation, which builds predictive models to estimate user preference on both items and item attributes; (2) Action, which learns a dialogue policy to determine whether to ask attributes or recommend items, based on Estimation stage and conversation history; and (3) Reflection, which updates the recommender model when a user rejects the recommendations made by the Action stage. We present two conversation scenarios on binary and enumerated questions, and conduct extensive experiments on two datasets from Yelp and LastFM, for each scenario, respectively. Our experiments demonstrate significant improvements over the state-of-the-art method CRM [32], corresponding to fewer conversation turns and a higher level of recommendation hits.
Tasks Recommendation Systems
Published 2020-02-21
URL https://arxiv.org/abs/2002.09102v1
PDF https://arxiv.org/pdf/2002.09102v1.pdf
PWC https://paperswithcode.com/paper/estimation-action-reflection-towards-deep

Learning ergodic averages in chaotic systems

Title Learning ergodic averages in chaotic systems
Authors Francisco Huhn, Luca Magri
Abstract We propose a physics-informed machine learning method to predict the time average of a chaotic attractor. The method is based on the hybrid echo state network (hESN). We assume that the system is ergodic, so the time average is equal to the ergodic average. Compared to conventional echo state networks (ESN) (purely data-driven), the hESN uses additional information from an incomplete, or imperfect, physical model. We evaluate the performance of the hESN and compare it to that of an ESN. This approach is demonstrated on a chaotic time-delayed thermoacoustic system, where the inclusion of a physical model significantly improves the accuracy of the prediction, reducing the relative error from 48% to 7%. This improvement is obtained at the low extra cost of solving two ordinary differential equations. This framework shows the potential of using machine learning techniques combined with prior physical knowledge to improve the prediction of time-averaged quantities in chaotic systems.
Published 2020-01-09
URL https://arxiv.org/abs/2001.04027v1
PDF https://arxiv.org/pdf/2001.04027v1.pdf
PWC https://paperswithcode.com/paper/learning-ergodic-averages-in-chaotic-systems

APAC-Net: Alternating the Population and Agent Control via Two Neural Networks to Solve High-Dimensional Stochastic Mean Field Games

Title APAC-Net: Alternating the Population and Agent Control via Two Neural Networks to Solve High-Dimensional Stochastic Mean Field Games
Authors Alex Tong Lin, Samy Wu Fung, Wuchen Li, Levon Nurbekyan, Stanley J. Osher
Abstract We present APAC-Net, an alternating population and agent control neural network for solving stochastic mean field games (MFGs). Our algorithm is geared toward high-dimensional instances MFGs that are beyond reach with existing solution methods. We achieve this in two steps. First, we take advantage of the underlying variational primal-dual structure that MFGs exhibit and phrase it as a convex-concave saddle point problem. Second, we parameterize the value and density functions by two neural networks, respectively. By phrasing the problem in this manner, solving the MFG can be interpreted as a special case of training a generative adversarial generative network (GAN). We show the potential of our method on up to 50-dimensional MFG problems.
Published 2020-02-24
URL https://arxiv.org/abs/2002.10113v1
PDF https://arxiv.org/pdf/2002.10113v1.pdf
PWC https://paperswithcode.com/paper/apac-net-alternating-the-population-and-agent

EikoNet: Solving the Eikonal equation with Deep Neural Networks

Title EikoNet: Solving the Eikonal equation with Deep Neural Networks
Authors Jonathan D. Smith, Kamyar Azizzadenesheli, Zachary E. Ross
Abstract The recent deep learning revolution has created an enormous opportunity for accelerating compute capabilities in the context of physics-based simulations. Here, we propose EikoNet, a deep learning approach to solving the Eikonal equation, which characterizes the first-arrival-time field in heterogeneous 3D velocity structures. Our grid-free approach allows for rapid determination of the travel time between any two points within a continuous 3D domain. These travel time solutions are allowed to violate the differential equation - which casts the problem as one of optimization - with the goal of finding network parameters that minimize the degree to which the equation is violated. In doing so, the method exploits the differentiability of neural networks to calculate the spatial gradients analytically, meaning the network can be trained on its own without ever needing solutions from a finite difference algorithm. EikoNet is rigorously tested on several velocity models and sampling methods to demonstrate robustness and versatility. Training and inference are highly parallelized, making the approach well-suited for GPUs. EikoNet has low memory overhead, and further avoids the need for travel-time lookup tables. The developed approach has important applications to earthquake hypocenter inversion, ray multi-pathing, and tomographic modeling, as well as to other fields beyond seismology where ray tracing is essential.
Published 2020-03-25
URL https://arxiv.org/abs/2004.00361v1
PDF https://arxiv.org/pdf/2004.00361v1.pdf
PWC https://paperswithcode.com/paper/eikonet-solving-the-eikonal-equation-with

Zeroth-order Optimization on Riemannian Manifolds

Title Zeroth-order Optimization on Riemannian Manifolds
Authors Jiaxiang Li, Krishnakumar Balasubramanian, Shiqian Ma
Abstract We propose and analyze zeroth-order algorithms for optimization over Riemannian manifolds, where we observe only potentially noisy evaluations of the objective function. Our approach is based on estimating the Riemannian gradient from the objective function evaluations. We consider three settings for the objective function: (i) deterministic and smooth, (ii) stochastic and smooth, and (iii) composition of smooth and non-smooth parts. For each of the setting, we characterize the oracle complexity of our algorithm to obtain appropriately defined notions of $\epsilon$-stationary points. Notably, our complexities are independent of the ambient dimension of the Euclidean space in which the manifold is embedded in, and only depend on the intrinsic dimension of the manifold. As a proof of concept, we demonstrate the applicability of our method to the problem of black-box attacks to deep neural networks, by providing simulation and real-world image data based experimental results.
Published 2020-03-25
URL https://arxiv.org/abs/2003.11238v1
PDF https://arxiv.org/pdf/2003.11238v1.pdf
PWC https://paperswithcode.com/paper/zeroth-order-optimization-on-riemannian

Learning and Solving Regular Decision Processes

Title Learning and Solving Regular Decision Processes
Authors Eden Abadi, Ronen I. Brafman
Abstract Regular Decision Processes (RDPs) are a recently introduced model that extends MDPs with non-Markovian dynamics and rewards. The non-Markovian behavior is restricted to depend on regular properties of the history. These can be specified using regular expressions or formulas in linear dynamic logic over finite traces. Fully specified RDPs can be solved by compiling them into an appropriate MDP. Learning RDPs from data is a challenging problem that has yet to be addressed, on which we focus in this paper. Our approach rests on a new representation for RDPs using Mealy Machines that emit a distribution and an expected reward for each state-action pair. Building on this representation, we combine automata learning techniques with history clustering to learn such a Mealy machine and solve it by adapting MCTS to it. We empirically evaluate this approach, demonstrating its feasibility.
Published 2020-03-02
URL https://arxiv.org/abs/2003.01008v1
PDF https://arxiv.org/pdf/2003.01008v1.pdf
PWC https://paperswithcode.com/paper/learning-and-solving-regular-decision

Volumetric parcellation of the right ventricle for regional geometric and functional assessment

Title Volumetric parcellation of the right ventricle for regional geometric and functional assessment
Authors Gabriel Bernardino, Amir Hodzic, Helene Langet, Mathieu De Craene, Miguel Angel González Ballester, Eric Saloux, Bart Bijnens
Abstract In clinical practice, assessment of right ventricle (RV) is primarily done through its global volume, given it is a standardised measurement, and has a good reproducibility in 3D modalities such as MRI and 3D echocardiography. However, many illness produce regionalchanges and therefore a local analysis could provide a better tool for understanding and diagnosis of illnesses. Current regional clinical measurements are 2D linear dimensions, and suffer of low reproducibility due to the difficulty to identify landmarks in the RV, specially in echocardiographic images due to its noise and artefacts. We proposed an automatic method for parcellating the RV cavity and compute regional volumes and ejection fractions in three regions: apex, inlet and outflow. We tested the reproducibility in 3D echocardiographic images. We also present a synthetic mesh-deformation method to generate a groundtruth dataset for validating the ability of the method to capture different types of remodelling. Results showed an acceptable intra-observer reproduciblity (<10%) but a higher inter-observer(>10%). The synthetic dataset allowed to identify that the method was capable of assessing global dilatations, and local dilatations in the circumferential direction but not longitudinal elongations
Published 2020-03-18
URL https://arxiv.org/abs/2003.08423v1
PDF https://arxiv.org/pdf/2003.08423v1.pdf
PWC https://paperswithcode.com/paper/volumetric-parcellation-of-the-right

Incremental Few-Shot Object Detection

Title Incremental Few-Shot Object Detection
Authors Juan-Manuel Perez-Rua, Xiatian Zhu, Timothy Hospedales, Tao Xiang
Abstract Most existing object detection methods rely on the availability of abundant labelled training samples per class and offline model training in a batch mode. These requirements substantially limit their scalability to open-ended accommodation of novel classes with limited labelled training data. We present a study aiming to go beyond these limitations by considering the Incremental Few-Shot Detection (iFSD) problem setting, where new classes must be registered incrementally (without revisiting base classes) and with few examples. To this end we propose OpeN-ended Centre nEt (ONCE), a detector designed for incrementally learning to detect novel class objects with few examples. This is achieved by an elegant adaptation of the CentreNet detector to the few-shot learning scenario, and meta-learning a class-specific code generator model for registering novel classes. ONCE fully respects the incremental learning paradigm, with novel class registration requiring only a single forward pass of few-shot training samples, and no access to base classes – thus making it suitable for deployment on embedded devices. Extensive experiments conducted on both the standard object detection and fashion landmark detection tasks show the feasibility of iFSD for the first time, opening an interesting and very important line of research.
Tasks Few-Shot Learning, Few-Shot Object Detection, Meta-Learning, Object Detection
Published 2020-03-10
URL https://arxiv.org/abs/2003.04668v2
PDF https://arxiv.org/pdf/2003.04668v2.pdf
PWC https://paperswithcode.com/paper/incremental-few-shot-object-detection

A Deep Learning Algorithm for High-Dimensional Exploratory Item Factor Analysis

Title A Deep Learning Algorithm for High-Dimensional Exploratory Item Factor Analysis
Authors Christopher J. Urban, Daniel J. Bauer
Abstract Deep learning methods are the gold standard for non-linear statistical modeling in computer vision and in natural language processing but are rarely used in psychometrics. To bridge this gap, we present a novel deep learning algorithm for exploratory item factor analysis (IFA). Our approach combines a deep artificial neural network (ANN) model called a variational autoencoder (VAE) with recent work that uses regularization for exploratory factor analysis. We first provide overviews of ANNs and VAEs. We then describe how to conduct exploratory IFA with a VAE and demonstrate our approach in two empirical examples and in two simulated examples. Our empirical results were consistent with existing psychological theory across random starting values. Our simulations suggest that the VAE consistently recovers the data generating factor pattern with moderate-sized samples. Secondary loadings were underestimated with a complex factor structure and intercept parameter estimates were moderately biased with both simple and complex factor structures. All models converged in minutes, even with hundreds of thousands of observations, hundreds of items, and tens of factors. We conclude that the VAE offers a powerful new approach to fitting complex statistical models in psychological and educational measurement.
Published 2020-01-22
URL https://arxiv.org/abs/2001.07859v1
PDF https://arxiv.org/pdf/2001.07859v1.pdf
PWC https://paperswithcode.com/paper/a-deep-learning-algorithm-for-high

Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems

Title Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems
Authors Wang-Cheng Kang, Derek Zhiyuan Cheng, Ting Chen, Xinyang Yi, Dong Lin, Lichan Hong, Ed H. Chi
Abstract Recommender system models often represent various sparse features like users, items, and categorical features via embeddings. A standard approach is to map each unique feature value to an embedding vector. The size of the produced embedding table grows linearly with the size of the vocabulary. Therefore, a large vocabulary inevitably leads to a gigantic embedding table, creating two severe problems: (i) making model serving intractable in resource-constrained environments; (ii) causing overfitting problems. In this paper, we seek to learn highly compact embeddings for large-vocab sparse features in recommender systems (recsys). First, we show that the novel Differentiable Product Quantization (DPQ) approach can generalize to recsys problems. In addition, to better handle the power-law data distribution commonly seen in recsys, we propose a Multi-Granular Quantized Embeddings (MGQE) technique which learns more compact embeddings for infrequent items. We seek to provide a new angle to improve recommendation performance with compact model sizes. Extensive experiments on three recommendation tasks and two datasets show that we can achieve on par or better performance, with only ~20% of the original model size.
Tasks Quantization, Recommendation Systems
Published 2020-02-20
URL https://arxiv.org/abs/2002.08530v1
PDF https://arxiv.org/pdf/2002.08530v1.pdf
PWC https://paperswithcode.com/paper/learning-multi-granular-quantized-embeddings
comments powered by Disqus