Paper Group ANR 1346
Explainability in Human-Agent Systems. Panoptic Image Annotation with a Collaborative Assistant. Distributed Variational Bayesian Algorithms for Extended Object Tracking. High Frequency Residual Learning for Multi-Scale Image Classification. Algorithm Portfolio for Individual-based Surrogate-Assisted Evolutionary Algorithms. Importance of spatial p …
Explainability in Human-Agent Systems
| Title | Explainability in Human-Agent Systems |
| Authors | Avi Rosenfeld, Ariella Richardson |
| Abstract | This paper presents a taxonomy of explainability in Human-Agent Systems. We consider fundamental questions about the Why, Who, What, When and How of explainability. First, we define explainability, and its relationship to the related terms of interpretability, transparency, explicitness, and faithfulness. These definitions allow us to answer why explainability is needed in the system, whom it is geared to and what explanations can be generated to meet this need. We then consider when the user should be presented with this information. Last, we consider how objective and subjective measures can be used to evaluate the entire system. This last question is the most encompassing as it will need to evaluate all other issues regarding explainability. |
| Tasks | |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08123v1 |
| http://arxiv.org/pdf/1904.08123v1.pdf | |
| PWC | https://paperswithcode.com/paper/explainability-in-human-agent-systems |
| Repo | |
| Framework | |
Panoptic Image Annotation with a Collaborative Assistant
| Title | Panoptic Image Annotation with a Collaborative Assistant |
| Authors | Jasper R. R. Uijlings, Mykhaylo Andriluka, Vittorio Ferrari |
| Abstract | This paper aims to reduce the time to annotate images for panoptic segmentation, which requires annotating segmentation masks and class labels for all object instances and stuff regions. We formulate our approach as a collaborative process between an annotator and an automated assistant who take turns to jointly annotate an image using a predefined pool of segments. Actions performed by the annotator serve as a strong contextual signal. The assistant intelligently reacts to this signal by annotating other parts of the image on its own, which reduces the amount of work required by the annotator. We perform thorough experiments on the COCO panoptic dataset, both in simulation and with human annotators. These demonstrate that our approach is 5x faster than manual polygon drawing tools, and is also significantly faster than the recent machine-assisted interface of [Andriluka ACMMM 2018]. Furthermore, we show on ADE20k that our method can be used to efficiently annotate new datasets, bootstrapping from a very small amount of annotated data. |
| Tasks | Panoptic Segmentation |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.06798v2 |
| https://arxiv.org/pdf/1906.06798v2.pdf | |
| PWC | https://paperswithcode.com/paper/panoptic-image-annotation-with-a |
| Repo | |
| Framework | |
Distributed Variational Bayesian Algorithms for Extended Object Tracking
| Title | Distributed Variational Bayesian Algorithms for Extended Object Tracking |
| Authors | Junhao Hua, Chunguang Li |
| Abstract | This paper is concerned with the problem of distributed extended object tracking, which aims to collaboratively estimate the state and extension of an object by a network of nodes. In traditional tracking applications, most approaches consider an object as a point source of measurements due to limited sensor resolution capabilities. Recently, some studies consider the extended objects, which are spatially structured, i.e., multiple resolution cells are occupied by an object. In this setting, multiple measurements are generated by each object per time step. In this paper, we present a Bayesian model for extended object tracking problem in a sensor network. In this model, the object extension is represented by a symmetric positive definite random matrix, and we assume that the measurement noise exists but is unknown. Using this Bayesian model, we first propose a novel centralized algorithm for extended object tracking based on variational Bayesian methods. Then, we extend it to the distributed scenario based on the alternating direction method of multipliers (ADMM) technique. The proposed algorithms can simultaneously estimate the extended object state (the kinematic state and extension) and the measurement noise covariance. Simulations on both extended object tracking and group target tracking are given to verify the effectiveness of the proposed model and algorithms. |
| Tasks | Object Tracking |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.00182v1 |
| http://arxiv.org/pdf/1903.00182v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-variational-bayesian-algorithms |
| Repo | |
| Framework | |
High Frequency Residual Learning for Multi-Scale Image Classification
| Title | High Frequency Residual Learning for Multi-Scale Image Classification |
| Authors | Bowen Cheng, Rong Xiao, Jianfeng Wang, Thomas Huang, Lei Zhang |
| Abstract | We present a novel high frequency residual learning framework, which leads to a highly efficient multi-scale network (MSNet) architecture for mobile and embedded vision problems. The architecture utilizes two networks: a low resolution network to efficiently approximate low frequency components and a high resolution network to learn high frequency residuals by reusing the upsampled low resolution features. With a classifier calibration module, MSNet can dynamically allocate computation resources during inference to achieve a better speed and accuracy trade-off. We evaluate our methods on the challenging ImageNet-1k dataset and observe consistent improvements over different base networks. On ResNet-18 and MobileNet with alpha=1.0, MSNet gains 1.5% accuracy over both architectures without increasing computations. On the more efficient MobileNet with alpha=0.25, our method gains 3.8% accuracy with the same amount of computations. |
| Tasks | Calibration, Image Classification |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.02649v1 |
| https://arxiv.org/pdf/1905.02649v1.pdf | |
| PWC | https://paperswithcode.com/paper/high-frequency-residual-learning-for-multi |
| Repo | |
| Framework | |
Algorithm Portfolio for Individual-based Surrogate-Assisted Evolutionary Algorithms
| Title | Algorithm Portfolio for Individual-based Surrogate-Assisted Evolutionary Algorithms |
| Authors | Hao Tong, Jialin Liu, Xin Yao |
| Abstract | Surrogate-assisted evolutionary algorithms (SAEAs) are powerful optimisation tools for computationally expensive problems (CEPs). However, a randomly selected algorithm may fail in solving unknown problems due to no free lunch theorems, and it will cause more computational resource if we re-run the algorithm or try other algorithms to get a much solution, which is more serious in CEPs. In this paper, we consider an algorithm portfolio for SAEAs to reduce the risk of choosing an inappropriate algorithm for CEPs. We propose two portfolio frameworks for very expensive problems in which the maximal number of fitness evaluations is only 5 times of the problem’s dimension. One framework named Par-IBSAEA runs all algorithm candidates in parallel and a more sophisticated framework named UCB-IBSAEA employs the Upper Confidence Bound (UCB) policy from reinforcement learning to help select the most appropriate algorithm at each iteration. An effective reward definition is proposed for the UCB policy. We consider three state-of-the-art individual-based SAEAs on different problems and compare them to the portfolios built from their instances on several benchmark problems given limited computation budgets. Our experimental studies demonstrate that our proposed portfolio frameworks significantly outperform any single algorithm on the set of benchmark problems. |
| Tasks | |
| Published | 2019-04-22 |
| URL | https://arxiv.org/abs/1904.09813v2 |
| https://arxiv.org/pdf/1904.09813v2.pdf | |
| PWC | https://paperswithcode.com/paper/algorithm-portfolio-for-individual-based |
| Repo | |
| Framework | |
Importance of spatial predictor variable selection in machine learning applications – Moving from data reproduction to spatial prediction
| Title | Importance of spatial predictor variable selection in machine learning applications – Moving from data reproduction to spatial prediction |
| Authors | Hanna Meyer, Christoph Reudenbach, Stephan Wöllauer, Thomas Nauss |
| Abstract | Machine learning algorithms find frequent application in spatial prediction of biotic and abiotic environmental variables. However, the characteristics of spatial data, especially spatial autocorrelation, are widely ignored. We hypothesize that this is problematic and results in models that can reproduce training data but are unable to make spatial predictions beyond the locations of the training samples. We assume that not only spatial validation strategies but also spatial variable selection is essential for reliable spatial predictions. We introduce two case studies that use remote sensing to predict land cover and the leaf area index for the “Marburg Open Forest”, an open research and education site of Marburg University, Germany. We use the machine learning algorithm Random Forests to train models using non-spatial and spatial cross-validation strategies to understand how spatial variable selection affects the predictions. Our findings confirm that spatial cross-validation is essential in preventing overoptimistic model performance. We further show that highly autocorrelated predictors (such as geolocation variables, e.g. latitude, longitude) can lead to considerable overfitting and result in models that can reproduce the training data but fail in making spatial predictions. The problem becomes apparent in the visual assessment of the spatial predictions that show clear artefacts that can be traced back to a misinterpretation of the spatially autocorrelated predictors by the algorithm. Spatial variable selection could automatically detect and remove such variables that lead to overfitting, resulting in reliable spatial prediction patterns and improved statistical spatial model performance. We conclude that in addition to spatial validation, a spatial variable selection must be considered in spatial predictions of ecological data to produce reliable predictions. |
| Tasks | |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.07805v1 |
| https://arxiv.org/pdf/1908.07805v1.pdf | |
| PWC | https://paperswithcode.com/paper/190807805 |
| Repo | |
| Framework | |
Associated Learning: Decomposing End-to-end Backpropagation based on Auto-encoders and Target Propagation
| Title | Associated Learning: Decomposing End-to-end Backpropagation based on Auto-encoders and Target Propagation |
| Authors | Yu-Wei Kao, Hung-Hsuan Chen |
| Abstract | Backpropagation has been widely used in deep learning approaches, but it is inefficient and sometimes unstable because of backward locking and vanishing/exploding gradient problems, especially when the gradient flow is long. Additionally, updating all edge weights based on a single objective seems biologically implausible. In this paper, we introduce a novel biologically motivated learning structure called Associated Learning, which modularizes the network into smaller components, each of which has a local objective. Because the objectives are mutually independent, Associated Learning can learn the parameters independently and simultaneously when these parameters belong to different components. Surprisingly, training deep models by Associated Learning yields comparable accuracies to models trained using typical backpropagation methods, which aims at fitting the target variable directly. Moreover, probably because the gradient flow of each component is short, deep networks can still be trained with Associated Learning even when some of the activation functions are sigmoid-a situation that usually results in the vanishing gradient problem when using typical backpropagation. We also found that the Associated Learning generates better metafeatures, which we demonstrated both quantitatively (via inter-class and intra-class distance comparisons in the hidden layers) and qualitatively (by visualizing the hidden layers using t-SNE). |
| Tasks | |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05560v2 |
| https://arxiv.org/pdf/1906.05560v2.pdf | |
| PWC | https://paperswithcode.com/paper/associated-learning-decomposing-end-to-end |
| Repo | |
| Framework | |
Channel adversarial training for speaker verification and diarization
| Title | Channel adversarial training for speaker verification and diarization |
| Authors | Chau Luu, Peter Bell, Steve Renals |
| Abstract | Previous work has encouraged domain-invariance in deep speaker embedding by adversarially classifying the dataset or labelled environment to which the generated features belong. We propose a training strategy which aims to produce features that are invariant at the granularity of the recording or channel, a finer grained objective than dataset- or environment-invariance. By training an adversary to predict whether pairs of same-speaker embeddings belong to the same recording in a Siamese fashion, learned features are discouraged from utilizing channel information that may be speaker discriminative during training. Experiments for verification on VoxCeleb and diarization and verification on CALLHOME show promising improvements over a strong baseline in addition to outperforming a dataset-adversarial model. The VoxCeleb model in particular performs well, achieving a $4%$ relative improvement in EER over a Kaldi baseline, while using a similar architecture and less training data. |
| Tasks | Speaker Verification |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11643v1 |
| https://arxiv.org/pdf/1910.11643v1.pdf | |
| PWC | https://paperswithcode.com/paper/channel-adversarial-training-for-speaker |
| Repo | |
| Framework | |
A human-inspired recognition system for premodern Japanese historical documents
| Title | A human-inspired recognition system for premodern Japanese historical documents |
| Authors | Anh Duc Le, Tarin Clanuwat, Asanobu Kitamoto |
| Abstract | Recognition of historical documents is a challenging problem due to the noised, damaged characters and background. However, in Japanese historical documents, not only contains the mentioned problems, pre-modern Japanese characters were written in cursive and are connected. Therefore, character segmentation based methods do not work well. This leads to the idea of creating a new recognition system. In this paper, we propose a human-inspired document reading system to recognize multiple lines of premodern Japanese historical documents. During the reading, people employ eyes movement to determine the start of a text line. Then, they move the eyes from the current character/word to the next character/word. They can also determine the end of a line or skip a figure to move to the next line. The eyes movement integrates with visual processing to operate the reading process in the brain. We employ attention-based encoder-decoder to implement this recognition system. First, the recognition system detects where to start a text line. Second, the system scans and recognize character by character until the text line is completed. Then, the system continues to detect the start of the next text line. This process is repeated until reading the whole document. We tested our human-inspired recognition system on the pre-modern Japanese historical document provide by the PRMU Kuzushiji competition. The results of the experiments demonstrate the superiority and effectiveness of our proposed system by achieving Sequence Error Rate of 9.87% and 53.81% on level 2 and level 3 of the dataset, respectively. These results outperform to any other systems participated in the PRMU Kuzushiji competition. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05377v1 |
| https://arxiv.org/pdf/1905.05377v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-human-inspired-recognition-system-for |
| Repo | |
| Framework | |
STANCY: Stance Classification Based on Consistency Cues
| Title | STANCY: Stance Classification Based on Consistency Cues |
| Authors | Kashyap Popat, Subhabrata Mukherjee, Andrew Yates, Gerhard Weikum |
| Abstract | Controversial claims are abundant in online media and discussion forums. A better understanding of such claims requires analyzing them from different perspectives. Stance classification is a necessary step for inferring these perspectives in terms of supporting or opposing the claim. In this work, we present a neural network model for stance classification leveraging BERT representations and augmenting them with a novel consistency constraint. Experiments on the Perspectrum dataset, consisting of claims and users’ perspectives from various debate websites, demonstrate the effectiveness of our approach over state-of-the-art baselines. |
| Tasks | |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06048v1 |
| https://arxiv.org/pdf/1910.06048v1.pdf | |
| PWC | https://paperswithcode.com/paper/stancy-stance-classification-based-on |
| Repo | |
| Framework | |
Predicting Individual Responses to Vasoactive Medications in Children with Septic Shock
| Title | Predicting Individual Responses to Vasoactive Medications in Children with Septic Shock |
| Authors | Nicole Fronda, Jessica Asencio, Cameron Carlin, David Ledbetter, Melissa Aczon, Randall Wetzel, Barry Markovitz |
| Abstract | Objective: Predict individual septic children’s personalized physiologic responses to vasoactive titrations by training a Recurrent Neural Network (RNN) using EMR data. Materials and Methods: This study retrospectively analyzed EMR of patients admitted to a pediatric ICU from 2009 to 2017. Data included charted time series vitals, labs, drugs, and interventions of children with septic shock treated with dopamine, epinephrine, or norepinephrine. A RNN was trained to predict responses in heart rate (HR), systolic blood pressure (SBP), diastolic blood pressure (DBP) and mean arterial pressure (MAP) to 8,640 titrations during 652 septic episodes and evaluated on a holdout set of 3,883 titrations during 254 episodes. A linear regression model using titration data as its sole input was also developed and compared to the RNN model. Evaluation methods included the correlation coefficient between actual physiologic responses and RNN predictions, mean absolute error (MAE), and area under the receiver operating characteristic curve (AUC). Results: The actual physiologic responses displayed significant variability and were more accurately predicted by the RNN model than by titration alone (r=0.20 vs r=0.05, p<0.01). The RNN showed MAE and AUC improvements over the linear model. The RNN’s MAEs associated with dopamine and epinephrine were 1-3% lower than the linear regression model MAE for HR, SBP, DBP, and MAP. Across all vitals vasoactives, the RNN achieved 1-19% AUC improvement over the linear model. Conclusion: This initial attempt in pediatric critical care to predict individual physiologic responses to vasoactive dose changes in children with septic shock demonstrated an RNN model showed some improvement over a linear model. While not yet clinically applicable, further development may assist clinical administration of vasoactive medications in children with septic shock. |
| Tasks | Time Series |
| Published | 2019-01-15 |
| URL | http://arxiv.org/abs/1901.10400v1 |
| http://arxiv.org/pdf/1901.10400v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-individual-responses-to-vasoactive |
| Repo | |
| Framework | |
Data Management for Causal Algorithmic Fairness
| Title | Data Management for Causal Algorithmic Fairness |
| Authors | Babak Salimi, Bill Howe, Dan Suciu |
| Abstract | Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflects discrimination, suggesting a data management problem. In this paper, we first make a distinction between associational and causal definitions of fairness in the literature and argue that the concept of fairness requires causal reasoning. We then review existing works and identify future opportunities for applying data management techniques to causal algorithmic fairness. |
| Tasks | |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.07924v3 |
| https://arxiv.org/pdf/1908.07924v3.pdf | |
| PWC | https://paperswithcode.com/paper/data-management-for-causal-algorithmic |
| Repo | |
| Framework | |
On the Sample Complexity of Learning Sum-Product Networks
| Title | On the Sample Complexity of Learning Sum-Product Networks |
| Authors | Ishaq Aden-Ali, Hassan Ashtiani |
| Abstract | Sum-Product Networks (SPNs) can be regarded as a form of deep graphical models that compactly represent deeply factored and mixed distributions. An SPN is a rooted directed acyclic graph (DAG) consisting of a set of leaves (corresponding to base distributions), a set of sum nodes (which represent mixtures of their children distributions) and a set of product nodes (representing the products of its children distributions). In this work, we initiate the study of the sample complexity of PAC-learning the set of distributions that correspond to SPNs. We show that the sample complexity of learning tree structured SPNs with the usual type of leaves (i.e., Gaussian or discrete) grows at most linearly (up to logarithmic factors) with the number of parameters of the SPN. More specifically, we show that the class of distributions that corresponds to tree structured Gaussian SPNs with $k$ mixing weights and $e$ ($d$-dimensional Gaussian) leaves can be learned within Total Variation error $\epsilon$ using at most $\widetilde{O}(\frac{ed^2+k}{\epsilon^2})$ samples. A similar result holds for tree structured SPNs with discrete leaves. We obtain the upper bounds based on the recently proposed notion of distribution compression schemes. More specifically, we show that if a (base) class of distributions $\mathcal{F}$ admits an “efficient” compression, then the class of tree structured SPNs with leaves from $\mathcal{F}$ also admits an efficient compression. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02765v2 |
| https://arxiv.org/pdf/1912.02765v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-sample-complexity-of-learning-sum |
| Repo | |
| Framework | |
Scalable Deep Generative Relational Models with High-Order Node Dependence
| Title | Scalable Deep Generative Relational Models with High-Order Node Dependence |
| Authors | Xuhui Fan, Bin Li, Scott Anthony Sisson, Caoyuan Li, Ling Chen |
| Abstract | We propose a probabilistic framework for modelling and exploring the latent structure of relational data. Given feature information for the nodes in a network, the scalable deep generative relational model (SDREM) builds a deep network architecture that can approximate potential nonlinear mappings between nodes’ feature information and the nodes’ latent representations. Our contribution is two-fold: (1) We incorporate high-order neighbourhood structure information to generate the latent representations at each node, which vary smoothly over the network. (2) Due to the Dirichlet random variable structure of the latent representations, we introduce a novel data augmentation trick which permits efficient Gibbs sampling. The SDREM can be used for large sparse networks as its computational cost scales with the number of positive links. We demonstrate its competitive performance through improved link prediction performance on a range of real-world datasets. |
| Tasks | Data Augmentation, Link Prediction |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01535v1 |
| https://arxiv.org/pdf/1911.01535v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-deep-generative-relational-models |
| Repo | |
| Framework | |
Graph Analysis and Graph Pooling in the Spatial Domain
| Title | Graph Analysis and Graph Pooling in the Spatial Domain |
| Authors | Mostafa Rahmani, Ping Li |
| Abstract | The spatial convolution layer which is widely used in the Graph Neural Networks (GNNs) aggregates the feature vector of each node with the feature vectors of its neighboring nodes. The GNN is not aware of the locations of the nodes in the global structure of the graph and when the local structures corresponding to different nodes are similar to each other, the convolution layer maps all those nodes to similar or same feature vectors in the continuous feature space. Therefore, the GNN cannot distinguish two graphs if their difference is not in their local structures. In addition, when the nodes are not labeled/attributed the convolution layers can fail to distinguish even different local structures. In this paper, we propose an effective solution to address this problem of the GNNs. The proposed approach leverages a spatial representation of the graph which makes the neural network aware of the differences between the nodes and also their locations in the graph. The spatial representation which is equivalent to a point-cloud representation of the graph is obtained by a graph embedding method. Using the proposed approach, the local feature extractor of the GNN distinguishes similar local structures in different locations of the graph and the GNN infers the topological structure of the graph from the spatial distribution of the locally extracted feature vectors. Moreover, the spatial representation is utilized to simplify the graph down-sampling problem. A new graph pooling method is proposed and it is shown that the proposed pooling method achieves competitive or better results in comparison with the state-of-the-art methods. |
| Tasks | Graph Embedding |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01589v1 |
| https://arxiv.org/pdf/1910.01589v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-analysis-and-graph-pooling-in-the |
| Repo | |
| Framework | |
