In general, graph representation learning methods assume that the train and test data come from the same distribution. In this work we consider an underexplored area of an otherwise rapidly developing field of graph representation learning: The task of out-of-distribution (OOD) graph classification, where train and test data have different distributions, with test data unavailable during training. Our work shows it is possible to use a causal model to learn approximately invariant representations that better extrapolate between train and test data. Finally, we conclude with synthetic and real-world dataset experiments showcasing the benefits of representations that are invariant to train/test distribution shifts.
Yale Center for Medical Informatics, Yale University（耶鲁大学耶鲁医学信息学中心）；VA Connecticut Healthcare System（康涅狄格州退伍军人医疗保健系统）；Yale School of Medicine（耶鲁大学医学院）
We study the functional task of deep learning image classification models and show that image classification requires extrapolation capabilities. This suggests that new theories have to be developed for the understanding of deep learning as the current theory assumes models are solely interpolating, leaving many questions about them unanswered. We investigate the pixel space and also the feature spaces extracted from images by trained models (in their hidden layers, including the 64-dimensional feature space in the last hidden layer of pre-trained residual neural networks), and also the featur…
Mila（米拉研究所）；University of Montreal（蒙特利尔大学）；Vector（Vector研究所）；University of Toronto（多伦多大学）；McGill University（麦吉尔大学）；Facebook AI Research（脸书人工智能研究院）
Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but also that shifts at test time may be more extreme in magnitude. In particular, we show that reducing differences in risk across training domains can reduce a model's sensitivity to a wide range of extreme distributional shifts, including the challenging setting where the input contains both causal and anti-causal ele…
Deep learning inspired by differential equations is a recent research trend and has marked the state of the art performance for many machine learning tasks. Among them, time-series modeling with neural controlled differential equations (NCDEs) is considered as a breakthrough. In many cases, NCDE-based models not only provide better accuracy than recurrent neural networks (RNNs) but also make it possible to process irregular time-series. In this work, we enhance NCDEs by redesigning their core part, i.e., generating a continuous path from a discrete time-series input. NCDEs typically use interp…
Extrapolation in reinforcement learning is the ability to generalize at test time given states that could never have occurred at training time. Here we consider four factors that lead to improved extrapolation in a simple Gridworld environment: (a) avoiding maximum Q-value (or other deterministic methods) for action choice at test time, (b) ego-centric representation of the Gridworld, (c) building rotational and mirror symmetry into the learning mechanism using rotational and mirror invariant convolution (rather than standard translation-invariant convolution), and (d) adding a maximum entropy…
The difficulty of multi-class classification generally increases with the number of classes. Using data from a subset of the classes, can we predict how well a classifier will scale with an increased number of classes? Under the assumption that the classes are sampled exchangeably, and under the assumption that the classifier is generative (e.g. QDA or Naive Bayes), we show that the expected accuracy when the classifier is trained on $k$ classes is the $k-1$st moment of a \emph{conditional accuracy distribution}, which can be estimated from data. This provides the theoretical foundation for pe…
Spatiotemporal graph neural process for reconstruction, extrapolation, and classification of cardiac trajectories
Department of Radiology, Lausanne University Hospital（放射科，洛桑大学医院）；University of Lausanne（洛桑大学）；Cardiovascular Department, Lausanne University Hospital（心血管科，洛桑大学医院）；Department of Medicine, Geneva University Hospital（医学部，日内瓦大学医院）；University of Geneva（日内瓦大学）；CIBM Center for Biomedical Imaging（生物医学成像中心）
Warsaw University of Technology（华沙理工大学）；Institute of Science and Technology Austria (ISTA)（奥地利科学技术研究所（ISTA））
We introduce LIMES, a new method for learning with non-stationary streaming data, inspired by the recent success of meta-learning. The main idea is not to attempt to learn a single classifier that would have to work well across all occurring data distributions, nor many separate classifiers, but to exploit a hybrid strategy: we learn a single set of model parameters from which a specific classifier for any specific data distribution is derived via classifier adaptation. Assuming a multi-class classification setting with class-prior shift, the adaptation step can be performed analytically with …
Learning using granularity statistical invariants for classification
School of Mathematics and Statistics, Hainan University（海南大学数学与统计学院）；School of Information and Communication Engineering, Hainan University（海南大学信息与通信工程学院）
Otto-von-Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）；Karl-Franzens-University Graz（格拉茨卡尔·弗朗岑斯大学）；Utrecht University（乌得勒支大学）
Density estimation is a versatile technique underlying many data mining tasks and techniques,ranging from exploration and presentation of static data, to probabilistic classification, or identifying changes or irregularities in streaming data. With the pervasiveness of embedded systems and digitisation, this latter type of streaming and evolving data becomes more important. Nevertheless, research in density estimation has so far focused on stationary data, leaving the task of of extrapolating and predicting density at time points outside a training window an open problem. For this task, Tempor…
In this work, we introduce a spatially transformed DenseNet architecture for transformation invariant classification of cancer tissue. Our architecture increases the accuracy of the base DenseNet architecture while adding the ability to operate in a transformation invariant way while simultaneously being simpler than other models that try to provide some form of invariance.
Multivariate time series classification is a task with increasing importance due to the proliferation of new problems in various fields (economy, health, energy, transport, crops, etc.) where a large number of information sources are available. Direct extrapolation of methods that traditionally worked in univariate environments cannot frequently be applied to obtain the best results in multivariate problems. This is mainly due to the inability of these methods to capture the relationships between the different variables that conform a multivariate time series. The multivariate proposals publis…
The field of Graph Signal Processing (GSP) has proposed tools to generalize harmonic analysis to complex domains represented through graphs. Among these tools are translations, which are required to define many others. Most works propose to define translations using solely the graph structure (i.e. edges). Such a problem is ill-posed in general as a graph conveys information about neighborhood but not about directions. In this paper, we propose to infer translations as edge-constrained operations that make a supervised classification problem invariant using a deep learning framework. As such, …
University College London（伦敦大学学院）；Braintree Ltd.（Braintree公司）
We propose an end-to-end deep learning learning model for graph classification and representation learning that is invariant to permutation of the nodes of the input graphs. We address the challenge of learning a fixed size graph representation for graphs of varying dimensions through a differentiable node attention pooling mechanism. In addition to a theoretical proof of its invariance to permutation, we provide empirical evidence demonstrating the statistically significant gain in accuracy when faced with an isomorphic graph classification task given only a small number of training examples.…
