Paper Group ANR 660
CASTNet: Community-Attentive Spatio-Temporal Networks for Opioid Overdose Forecasting. Approximate Inference for Fully Bayesian Gaussian Process Regression. Strategic Classification is Causal Modeling in Disguise. Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics. Optimising Individual-Treatment-Effect Using Bandits. …
CASTNet: Community-Attentive Spatio-Temporal Networks for Opioid Overdose Forecasting
| Title | CASTNet: Community-Attentive Spatio-Temporal Networks for Opioid Overdose Forecasting |
| Authors | Ali Mert Ertugrul, Yu-Ru Lin, Tugba Taskaya-Temizel |
| Abstract | Opioid overdose is a growing public health crisis in the United States. This crisis, recognized as “opioid epidemic,” has widespread societal consequences including the degradation of health, and the increase in crime rates and family problems. To improve the overdose surveillance and to identify the areas in need of prevention effort, in this work, we focus on forecasting opioid overdose using real-time crime dynamics. Previous work identified various types of links between opioid use and criminal activities, such as financial motives and common causes. Motivated by these observations, we propose a novel spatio-temporal predictive model for opioid overdose forecasting by leveraging the spatio-temporal patterns of crime incidents. Our proposed model incorporates multi-head attentional networks to learn different representation subspaces of features. Such deep learning architecture, called “community-attentive” networks, allows the prediction of a given location to be optimized by a mixture of groups (i.e., communities) of regions. In addition, our proposed model allows for interpreting what features, from what communities, have more contributions to predicting local incidents as well as how these communities are captured through forecasting. Our results on two real-world overdose datasets indicate that our model achieves superior forecasting performance and provides meaningful interpretations in terms of spatio-temporal relationships between the dynamics of crime and that of opioid overdose. |
| Tasks | |
| Published | 2019-05-12 |
| URL | https://arxiv.org/abs/1905.04714v3 |
| https://arxiv.org/pdf/1905.04714v3.pdf | |
| PWC | https://paperswithcode.com/paper/castnet-community-attentive-spatio-temporal |
| Repo | |
| Framework | |
Approximate Inference for Fully Bayesian Gaussian Process Regression
| Title | Approximate Inference for Fully Bayesian Gaussian Process Regression |
| Authors | Vidhi Lalchand, Carl Edward Rasmussen |
| Abstract | Learning in Gaussian Process models occurs through the adaptation of hyperparameters of the mean and the covariance function. The classical approach entails maximizing the marginal likelihood yielding fixed point estimates (an approach called \textit{Type II maximum likelihood} or ML-II). An alternative learning procedure is to infer the posterior over hyperparameters in a hierarchical specification of GPs we call \textit{Fully Bayesian Gaussian Process Regression} (GPR). This work considers two approximation schemes for the intractable hyperparameter posterior: 1) Hamiltonian Monte Carlo (HMC) yielding a sampling-based approximation and 2) Variational Inference (VI) where the posterior over hyperparameters is approximated by a factorized Gaussian (mean-field) or a full-rank Gaussian accounting for correlations between hyperparameters. We analyze the predictive performance for fully Bayesian GPR on a range of benchmark data sets. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/1912.13440v1 |
| https://arxiv.org/pdf/1912.13440v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-inference-for-fully-bayesian |
| Repo | |
| Framework | |
Strategic Classification is Causal Modeling in Disguise
| Title | Strategic Classification is Causal Modeling in Disguise |
| Authors | John Miller, Smitha Milli, Moritz Hardt |
| Abstract | Consequential decision-making incentivizes individuals to strategically adapt their behavior to the specifics of the decision rule. While a long line of work has viewed strategic adaptation as gaming and attempted to mitigate its effects, recent work has instead sought to design classifiers that incentivize individuals to improve a desired quality. Key to both accounts is a cost function that dictates which adaptations are rational to undertake. In this work, we develop a causal framework for strategic adaptation. Our causal perspective clearly distinguishes between gaming and improvement and reveals an important obstacle to incentive design. We prove any procedure for designing classifiers that incentivize improvement must inevitably solve a non-trivial causal inference problem. Moreover, we show a similar result holds for designing cost functions that satisfy the requirements of previous work. With the benefit of hindsight, our results show much of the prior work on strategic classification is causal modeling in disguise. |
| Tasks | Causal Inference, Decision Making |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.10362v3 |
| https://arxiv.org/pdf/1910.10362v3.pdf | |
| PWC | https://paperswithcode.com/paper/strategic-adaptation-to-classifiers-a-causal |
| Repo | |
| Framework | |
Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics
| Title | Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics |
| Authors | Mohammad Javad Khojasteh, Vikas Dhiman, Massimo Franceschetti, Nikolay Atanasov |
| Abstract | This paper focuses on learning a model of system dynamics online while satisfying safety constraints. Our motivation is to avoid offline system identification or hand-specified dynamics models and allow a system to safely and autonomously estimate and adapt its own model during online operation. Given streaming observations of the system state, we use Bayesian learning to obtain a distribution over the system dynamics. In turn, the distribution is used to optimize the system behavior and ensure safety with high probability, by specifying a chance constraint over a control barrier function. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.10116v1 |
| https://arxiv.org/pdf/1912.10116v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-safety-constraints-for-learned |
| Repo | |
| Framework | |
Optimising Individual-Treatment-Effect Using Bandits
| Title | Optimising Individual-Treatment-Effect Using Bandits |
| Authors | Jeroen Berrevoets, Sam Verboven, Wouter Verbeke |
| Abstract | Applying causal inference models in areas such as economics, healthcare and marketing receives great interest from the machine learning community. In particular, estimating the individual-treatment-effect (ITE) in settings such as precision medicine and targeted advertising has peaked in application. Optimising this ITE under the strong-ignorability-assumption – meaning all confounders expressing influence on the outcome of a treatment are registered in the data – is often referred to as uplift modeling (UM). While these techniques have proven useful in many settings, they suffer vividly in a dynamic environment due to concept drift. Take for example the negative influence on a marketing campaign when a competitor product is released. To counter this, we propose the uplifted contextual multi-armed bandit (U-CMAB), a novel approach to optimise the ITE by drawing upon bandit literature. Experiments on real and simulated data indicate that our proposed approach compares favourably against the state-of-the-art. All our code can be found online at https://github.com/vub-dl/u-cmab. |
| Tasks | Causal Inference |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07265v1 |
| https://arxiv.org/pdf/1910.07265v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimising-individual-treatment-effect-using |
| Repo | |
| Framework | |
Lung image segmentation by generative adversarial networks
| Title | Lung image segmentation by generative adversarial networks |
| Authors | Jiaxin Cai, Hongfeng Zhu |
| Abstract | Lung image segmentation plays an important role in computer-aid pulmonary diseases diagnosis and treatment. This paper proposed a lung image segmentation method by generative adversarial networks. We employed a variety of generative adversarial networks and use its capability of image translation to perform image segmentation. The generative adversarial networks was employed to translate the original lung image to the segmented image. The generative adversarial networks based segmentation method was test on real lung image data set. Experimental results shows that the proposed method is effective and outperform state-of-the art method. |
| Tasks | Semantic Segmentation |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.13033v1 |
| https://arxiv.org/pdf/1907.13033v1.pdf | |
| PWC | https://paperswithcode.com/paper/lung-image-segmentation-by-generative |
| Repo | |
| Framework | |
Efficient Global String Kernel with Random Features: Beyond Counting Substructures
| Title | Efficient Global String Kernel with Random Features: Beyond Counting Substructures |
| Authors | Lingfei Wu, Ian En-Hsu Yen, Siyu Huo, Liang Zhao, Kun Xu, Liang Ma, Shouling Ji, Charu Aggarwal |
| Abstract | Analysis of large-scale sequential data has been one of the most crucial tasks in areas such as bioinformatics, text, and audio mining. Existing string kernels, however, either (i) rely on local features of short substructures in the string, which hardly capture long discriminative patterns, (ii) sum over too many substructures, such as all possible subsequences, which leads to diagonal dominance of the kernel matrix, or (iii) rely on non-positive-definite similarity measures derived from the edit distance. Furthermore, while there have been works addressing the computational challenge with respect to the length of string, most of them still experience quadratic complexity in terms of the number of training samples when used in a kernel-based classifier. In this paper, we present a new class of global string kernels that aims to (i) discover global properties hidden in the strings through global alignments, (ii) maintain positive-definiteness of the kernel, without introducing a diagonal dominant kernel matrix, and (iii) have a training cost linear with respect to not only the length of the string but also the number of training string samples. To this end, the proposed kernels are explicitly defined through a series of different random feature maps, each corresponding to a distribution of random strings. We show that kernels defined this way are always positive-definite, and exhibit computational benefits as they always produce \emph{Random String Embeddings (RSE)} that can be directly used in any linear classification models. Our extensive experiments on nine benchmark datasets corroborate that RSE achieves better or comparable accuracy in comparison to state-of-the-art baselines, especially with the strings of longer lengths. In addition, we empirically show that RSE scales linearly with the increase of the number and the length of string. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11121v1 |
| https://arxiv.org/pdf/1911.11121v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-global-string-kernel-with-random |
| Repo | |
| Framework | |
Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators
| Title | Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators |
| Authors | Tien-Ju Yang, Vivienne Sze |
| Abstract | This paper describes various design considerations for deep neural networks that enable them to operate efficiently and accurately on processing-in-memory accelerators. We highlight important properties of these accelerators and the resulting design considerations using experiments conducted on various state-of-the-art deep neural networks with the large-scale ImageNet dataset. |
| Tasks | |
| Published | 2019-12-18 |
| URL | https://arxiv.org/abs/1912.12167v1 |
| https://arxiv.org/pdf/1912.12167v1.pdf | |
| PWC | https://paperswithcode.com/paper/design-considerations-for-efficient-deep |
| Repo | |
| Framework | |
Mark my Word: A Sequence-to-Sequence Approach to Definition Modeling
| Title | Mark my Word: A Sequence-to-Sequence Approach to Definition Modeling |
| Authors | Timothee Mickus, Denis Paperno, Mathieu Constant |
| Abstract | Defining words in a textual context is a useful task both for practical purposes and for gaining insight into distributed word representations. Building on the distributional hypothesis, we argue here that the most natural formalization of definition modeling is to treat it as a sequence-to-sequence task, rather than a word-to-sequence task: given an input sequence with a highlighted word, generate a contextually appropriate definition for it. We implement this approach in a Transformer-based sequence-to-sequence model. Our proposal allows to train contextualization and definition generation in an end-to-end fashion, which is a conceptual improvement over earlier works. We achieve state-of-the-art results both in contextual and non-contextual definition modeling. |
| Tasks | |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05715v1 |
| https://arxiv.org/pdf/1911.05715v1.pdf | |
| PWC | https://paperswithcode.com/paper/mark-my-word-a-sequence-to-sequence-approach |
| Repo | |
| Framework | |
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
| Title | State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations |
| Authors | Alex Lamb, Jonathan Binas, Anirudh Goyal, Sandeep Subramanian, Ioannis Mitliagkas, Denis Kazakov, Yoshua Bengio, Michael C. Mozer |
| Abstract | Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as the existence of adversarial examples that are misclassified despite being nearly identical to a training example, or the inability of recurrent sequence-processing nets to stay on track without teacher forcing. We introduce a method, which we refer to as \emph{state reification}, that involves modeling the distribution of hidden states over the training data and then projecting hidden states observed during testing toward this distribution. Our intuition is that if the network can remain in a familiar manifold of hidden space, subsequent layers of the net should be well trained to respond appropriately. We show that this state-reification method helps neural nets to generalize better, especially when labeled data are sparse, and also helps overcome the challenge of achieving robust generalization with adversarial training. |
| Tasks | |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1905.11382v1 |
| https://arxiv.org/pdf/1905.11382v1.pdf | |
| PWC | https://paperswithcode.com/paper/190511382 |
| Repo | |
| Framework | |
Active Multi-Information Source Bayesian Quadrature
| Title | Active Multi-Information Source Bayesian Quadrature |
| Authors | Alexandra Gessner, Javier Gonzalez, Maren Mahsereci |
| Abstract | Bayesian quadrature (BQ) is a sample-efficient probabilistic numerical method to solve integrals of expensive-to-evaluate black-box functions, yet so far,active BQ learning schemes focus merely on the integrand itself as information source, and do not allow for information transfer from cheaper, related functions. Here, we set the scene for active learning in BQ when multiple related information sources of variable cost (in input and source) are accessible. This setting arises for example when evaluating the integrand requires a complex simulation to be run that can be approximated by simulating at lower levels of sophistication and at lesser expense. We construct meaningful cost-sensitive multi-source acquisition rates as an extension to common utility functions from vanilla BQ (VBQ),and discuss pitfalls that arise from blindly generalizing. Furthermore, we show that the VBQ acquisition policy is a corner-case of all considered cost-sensitive acquisition schemes, which collapse onto one single de-generate policy in the case of one source and constant cost. In proof-of-concept experiments we scrutinize the behavior of our generalized acquisition functions. On an epidemiological model, we demonstrate that active multi-source BQ (AMS-BQ) allocates budget more efficiently than VBQ for learning the integral to a good accuracy. |
| Tasks | Active Learning |
| Published | 2019-03-27 |
| URL | https://arxiv.org/abs/1903.11331v2 |
| https://arxiv.org/pdf/1903.11331v2.pdf | |
| PWC | https://paperswithcode.com/paper/active-multi-information-source-bayesian |
| Repo | |
| Framework | |
Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks
| Title | Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks |
| Authors | Jinyong Hou, Xuejie Ding, Jeremiah D. Deng, Stephen Cranefield |
| Abstract | Current deep domain adaptation methods used in computer vision have mainly focused on learning discriminative and domain-invariant features across different domains. In this paper, we present a novel approach that bridges the domain gap by projecting the source and target domains into a common association space through an unsupervised ``cross-grafted representation stacking’’ (CGRS) mechanism. Specifically, we construct variational auto-encoders (VAE) for the two domains, and form bidirectional associations by cross-grafting the VAEs’ decoder stacks. Furthermore, generative adversarial networks (GAN) are employed for label alignment (LA), mapping the target domain data to the known label space of the source domain. The overall adaptation process hence consists of three phases: feature representation learning by VAEs, association generation, and association label alignment by GANs. Experimental results demonstrate that our CGRS-LA approach outperforms the state-of-the-art on a number of unsupervised domain adaptation benchmarks. | |
| Tasks | Domain Adaptation, Representation Learning, Unsupervised Domain Adaptation |
| Published | 2019-02-17 |
| URL | http://arxiv.org/abs/1902.06328v2 |
| http://arxiv.org/pdf/1902.06328v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-using-deep |
| Repo | |
| Framework | |
Mislabel Detection of Finnish Publication Ranks
| Title | Mislabel Detection of Finnish Publication Ranks |
| Authors | Anton Akusok, Mirka Saarela, Tommi Kärkkäinen, Kaj-Mikael Björk, Amaury Lendasse |
| Abstract | The paper proposes to analyze a data set of Finnish ranks of academic publication channels with Extreme Learning Machine (ELM). The purpose is to introduce and test recently proposed ELM-based mislabel detection approach with a rich set of features characterizing a publication channel. We will compare the architecture, accuracy, and, especially, the set of detected mislabels of the ELM-based approach to the corresponding reference results on the reference paper. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09094v1 |
| https://arxiv.org/pdf/1912.09094v1.pdf | |
| PWC | https://paperswithcode.com/paper/mislabel-detection-of-finnish-publication |
| Repo | |
| Framework | |
A Survey on Graph Kernels
| Title | A Survey on Graph Kernels |
| Authors | Nils M. Kriege, Fredrik D. Johansson, Christopher Morris |
| Abstract | Graph kernels have become an established and widely-used technique for solving classification tasks on graphs. This survey gives a comprehensive overview of techniques for kernel-based graph classification developed in the past 15 years. We describe and categorize graph kernels based on properties inherent to their design, such as the nature of their extracted graph features, their method of computation and their applicability to problems in practice. In an extensive experimental evaluation, we study the classification accuracy of a large suite of graph kernels on established benchmarks as well as new datasets. We compare the performance of popular kernels with several baseline methods and study the effect of applying a Gaussian RBF kernel to the metric induced by a graph kernel. In doing so, we find that simple baselines become competitive after this transformation on some datasets. Moreover, we study the extent to which existing graph kernels agree in their predictions (and prediction errors) and obtain a data-driven categorization of kernels as result. Finally, based on our experimental results, we derive a practitioner’s guide to kernel-based graph classification. |
| Tasks | Graph Classification |
| Published | 2019-03-28 |
| URL | https://arxiv.org/abs/1903.11835v2 |
| https://arxiv.org/pdf/1903.11835v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-on-graph-kernels |
| Repo | |
| Framework | |
Learning Vertex Convolutional Networks for Graph Classification
| Title | Learning Vertex Convolutional Networks for Graph Classification |
| Authors | Lu Bai, Lixin Cui, Shu Wu, Yuhang Jiao, Edwin R. Hancock |
| Abstract | In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of fixed-sized one-dimensional convolution filters on the grid structure. We show that the proposed model not only integrates the precise structural correspondence information between graphs but also minimises the loss of structural information residing on local-level vertices. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model. |
| Tasks | Graph Classification |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.09936v1 |
| http://arxiv.org/pdf/1902.09936v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-vertex-convolutional-networks-for |
| Repo | |
| Framework | |
