United States

Large capacity deep learning models are often prone to a high generalization gap when trained with a limited amount of labeled training data. A recent class of methods to address this problem uses various ways to construct a new training sample by mixing a pair (or more) of training samples. We propose PatchUp, a hidden state block-level regularization technique for Convolutional Neural Networks (CNNs), that is applied on selected contiguous blocks of feature maps from a random pair of samples. Our approach improves the robustness of CNN models against the manifold intrusion problem that may occur in other state-of-the-art mixing approaches. Moreover, since we are mixing the contiguous block of features in the hidden space, which has more dimensions than the input space, we obtain more diverse samples for training towards different dimensions. Our experiments on CIFAR10/100, SVHN, Tiny-ImageNet, and ImageNet using ResNet architectures including PreActResnet18/34, WRN-28-10, ResNet101/152 models show that PatchUp improves upon, or equals, the performance of current state-of-the-art regularizers for CNNs. We also show that PatchUp can provide a better generalization to deformed samples and is more robust against adversarial attacks.

AAAI 2022

PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

technical paper

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

We address the poor scalability of learning algorithms for orthogonal recurrent neural networks via the use of stochastic coordinate descent on the orthogonal group, leading to a cost per iteration that increases linearly with the number of recurrent states. This contrasts with the cubic dependency of typical feasible algorithms such as stochastic Riemannian gradient descent, which prohibits the use of big network architectures. Coordinate descent rotates successively two columns of the recurrent matrix. When the coordinate (i.e., indices of rotated columns) is selected uniformly at random at each iteration, we prove convergence of the algorithm under standard assumptions on the loss function, stepsize and minibatch noise. In addition, we numerically show that the Riemannian gradient has an approximately sparse structure. Leveraging this observation, we propose a variant of our proposed algorithm that relies on the Gauss-Southwell coordinate selection rule. Experiments on a benchmark recurrent neural network training problem show that the proposed approach is a very promising step towards the training of orthogonal recurrent neural networks with big architectures.

Coordinate Descent on the Orthogonal Group for Recurrent Neural Network Training

In this paper, we introduce VACA, a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available. Without making any parametric assumptions, VACA mimics the necessary properties of a Structural Causal Model (SCM) to provide a flexible and practical framework for approximating interventions (do-operator) and abduction-action-prediction steps. As a result, and as shown by our empirical results, VACA accurately approximates the interventional and counterfactual distributions on diverse SCMs. Finally, we apply VACA to evaluate counterfactual fairness in fair classification problems, as well as to learn fair classifiers without compromising performance.

VACA: Designing Variational Graph Autoencoders for Causal Queries

Submodular functions are at the core of many machine learning and data mining tasks. The underlying submodular functions for many of these tasks are decomposable, i.e., they are sum of several simple submodular functions. In many data intensive applications, however, the number of underlying submodular functions in the original function is so large that we need prohibitively large amount of time to process it and/or it does not even fit in the main memory. To overcome this issue, we introduce the notion of sparsification for decomposable submodular functions whose objective is to obtain an accurate approximation of the original function that is a (weighted) sum of only a few submodular functions. Our main result is a polynomial-time randomized sparsification algorithm such that the expected number of functions used in the output is independent of the number of underlying submodular functions in the original function. We also study the effectiveness of our algorithm under various constraints such as matroid and cardinality constraints. We complement our theoretical analysis with an empirical study of the performance of our algorithm.

Sparsification of Decomposable Submodular Functions

Neural ordinary differential equations (NODE) have been proposed as a continuous depth generalization to popular deep learning models such as Residual networks (ResNets). They provide parameter efficiency and automate the model selection process in deep learning models to some extent. However, they lack the much-required uncertainty modelling and robustness capabilities which are crucial for their use in several real-world applications such as autonomous driving and healthcare. We propose a novel and unique approach to model uncertainty in NODE by considering a distribution over the end-time T of the ODE solver. The proposed approach, latent time NODE (LT-NODE), treats T as a latent variable and apply Bayesian learning to obtain a posterior distribution over T from the data. In particular, we use variational inference to learn an approximate posterior and the model parameters. Prediction is done by considering the NODE representations from different samples of the posterior and can be done efficiently using a single forward pass. As T implicitly defines the depth of a NODE, posterior distribution over T would also help in model selection in NODE. We also propose, adaptive latent time NODE (ALT-NODE), which allow each data point to have a distinct posterior distribution over end-times. ALT-NODE uses amortized variational inference to learn an approximate posterior using inference networks. We demonstrate the effectiveness of the proposed approaches in modelling uncertainty and robustness through experiments on synthetic and several real-world image classification data.

Latent Time Neural Ordinary Differential Equations

We introduce three new generative models for time series that are based on Euler discretization of Stochastic Differential Equations (SDEs) and Wasserstein metrics. Two of these methods rely on the adaptation of generative adversarial networks (GANs) to time series. The third algorithm, called Conditional Euler Generator (CEGEN), minimizes a dedicated distance between the transition probability distributions over all time steps. In the context of ItÃ´ processes, we provide theoretical guarantees that minimizing this criterion implies accurate estimations of the drift and volatility parameters. Empirically, CEGEN outperforms state-of-the-art and GANs on both marginal and temporal dynamic metrics. Besides, correlation structures are accurately identified in high dimension. When few real data points are available, we verify the effectiveness of CEGEN when combined with transfer learning methods on model-based simulations. Finally, we illustrate the robustness of our methods on various real-world data sets.

Conditional Loss and Deep Euler Scheme for Time Series Generation

Off-policy sampling and experience replay are key for improving sample efficiency and scaling model-free temporal difference learning methods. When combined with function approximation, such as neural networks, this combination is known as the deadly triad and is potentially unstable. Recently, it has been shown that stability and good performance at scale can be achieved by combining emphatic weightings and multi-step updates. This approach, however, is generally limited to sampling complete trajectories in order, to compute the required emphatic weighting. In this paper we investigate how to combine emphatic weightings with non-sequential, off-line data sampled from a replay buffer. We develop a multi-step emphatic weighting that can be combined with replay, and a time-reversed n-step TD learning algorithm to learn the required emphatic weighting. We show that these state weightings reduce variance compared with prior approaches, while providing convergence guarantees. We tested the approach at scale on Atari 2600 video games, and observed that the new X-ETD(n) agent improved over baseline agents, highlighting both the scalability and broad applicability of our approach.

Learning Expected Emphatic Traces for Deep RL

When aggregating logically interconnected judgements from n agents, the result might be logically inconsistent. This phenomenon is known as the doctrinal paradox, which plays a central role in the field of judgement aggregation. Previous work has mostly focused on the worst-case analysis of the doctrinal paradox, leading to many impossibility results. Little is known about its likelihood of occurrence in practical settings,  except for the study under certain distributions by List in 2005. In this paper, we characterize the likelihood of the doctrinal paradox under a  general and realistic model called semi-random social choice framework (proposed by Xia in 2020). In the framework, agents' ground truth judgements can be arbitrarily correlated, while the noises are independent.  Our main theorem states that under mild conditions, the semi-random likelihood of the doctrinal paradox is either 0, exp(-Î˜(n)), Î˜(n\^~(-0.5)) or Î˜(1). This not only answers open questions by List in 2005, but also draws clear lines between situations with frequent paradoxes and with vanishing paradoxes.

The Semi-Random Likelihood of Doctrinal Paradoxes

Models in the supervised learning framework may capture rich and complex representations over the features that are hard for humans to interpret. Existing methods to explain such models are often specific to architectures and data where the features do not have a time-varying component. In this work, we propose TIME, a method to explain models that are inherently temporal in nature. Our approach (i) uses a model-agnostic permutation-based approach to analyze global feature importance, (ii) identifies the importance of salient features with respect to their temporal ordering as well as localized windows of influence, and (iii) uses hypothesis testing to provide statistical rigor.

Feature Importance Explanations for Temporal Black-Box Models

The majority of popular graph kernels is based on the concept of Haussler's R-convolution kernel and defines graph similarities in terms of mutual substructures. 
In this work, we enrich these similarity measures by considering graph filtrations:
Using meaningful orders on the set of edges, which allow to construct a sequence of nested graphs, we can consider a graph at multiple granularities. 
A key concept of our approach is to track graph features over the course of such graph resolutions. 
Rather than to simply compare frequencies of features in graphs, this allows for their comparison in terms of when and for how long they exist in the sequences. 
In this work, we propose a family of graph kernels that incorporate these existence intervals of features. 
While our approach can be applied to arbitrary graph features, we particularly highlight Weisfeiler-Lehman vertex labels, leading to efficient kernels. 
We show that using Weisfeiler-Lehman labels over certain filtrations strictly increases the expressive power over the ordinary Weisfeiler-Lehman procedure in terms of deciding graph isomorphism.
In fact, this result directly yields more powerful graph kernels based on such features and has implications to graph neural networks due to their close relationship to the Weisfeiler-Lehman method.
We empirically validate the expressive power of our graph kernels and show significant improvements over state-of-the-art graph kernels in terms of predictive performance on various real-world benchmark datasets.

Graph Filtration Kernels

Hierarchical SGD (H-SGD) has emerged as a new distributed SGD algorithm for multi-level communication networks. In H-SGD, before each global aggregation, workers send their updated local models to local servers for aggregations. Despite recent research efforts, the effect of local aggregation on global convergence still lacks theoretical understanding. In this work, we first introduce a new notion of "upward" and "downward" divergences. We then use it to conduct a novel analysis to obtain a worst-case convergence upper bound for two-level H-SGD with non-IID data, non-convex objective function, and stochastic gradient. By extending this result to the case with random grouping, we observe that this convergence upper bound of H-SGD is between the upper bounds of two single-level local SGD settings, with the number of local iterations equal to the local and global update periods in H-SGD, respectively. We refer to this as the "sandwich behavior". Furthermore, we extend our analytical approach based on "upward" and "downward" divergences to study the convergence for the general case of H-SGD with more than two levels, where the "sandwich behavior" still holds. Our theoretical results provide key insights of why local aggregation can be beneficial in improving the convergence of H-SGD.

Downloads

Next from AAAI 2022

Coordinate Descent on the Orthogonal Group for Recurrent Neural Network Training

Similar lecture

A Close Look at Deep Learning with Small Data

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2022

Coordinate Descent on the Orthogonal Group for Recurrent Neural Network Training

Similar lecture

A Close Look at Deep Learning with Small Data

Downloads