“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

A morphable model for the synthesis of 3D faces

Normalizing flows provide a general mechanism for defining expressive probability distributions, only requiring the specification of a (usually simple) base distribution and a series of bijective transformations. There has been much recent work on normalizing flows, ranging from improving their expressive power to expanding their application. We believe the field has now matured and is in need of a unified perspective. In this review, we attempt to provide such a perspective by describing flows through the lens of probabilistic modeling and inference. We place special emphasis on the fundamental principles of flow design, and discuss foundational topics such as expressive power and computational trade-offs. We also broaden the conceptual framing of flows by relating them to more general probability transformations. Lastly, we summarize the use of flows for tasks such as generative modeling, approximate inference, and supervised learning.

Normalizing Flows for Probabilistic Modeling and Inference

In this paper we introduce a novel, unified, open-source model interpretability library for PyTorch [12]. The library contains generic implementations of a number of gradient and perturbation-based attribution algorithms, also known as feature, neuron and layer importance algorithms, as well as a set of evaluation metrics for these algorithms. It can be used for both classification and non-classification models including graph-structured models built on Neural Networks (NN). In this paper we give a high-level overview of supported attribution algorithms and show how to perform memory-efficient and scalable computations. We emphasize that the three main characteristics of the library are multimodality, extensibility and ease of use. Multimodality supports different modality of inputs such as image, text, audio or video. Extensibility allows adding new algorithms and features. The library is also designed for easy understanding and use. Besides, we also introduce an interactive visualization tool called Captum Insights that is built on top of Captum library and allows sample-based model debugging and visualization using feature importance metrics.

Captum: A unified and generic model interpretability library for PyTorch.

In recent years, there has been a explosion in the amount of text data from a variety of sources. This volume of text is an invaluable source of information and knowledge which needs to be effectively summarized to be useful. Text summarization is the task of shortening a text document into a condensed version keeping all the important information and content of the original document. In this review, the main approaches to automatic text summarization are described. We review the different processes for summarization and describe the effectiveness and shortcomings of the different methods.

/pdf/text-summarization-techniques-a-brief-survey-43bjw9ear2.pdf

Text Summarization Techniques: A Brief Survey

We develop a fast algorithm for the Admixture of Poisson MRFs (APM) topic model [1] and propose a novel metric to directly evaluate this model. The APM topic model recently introduced by Inouye et al. [1] is the first topic model that allows for word dependencies within each topic unlike in previous topic models like LDA that assume independence between words within a topic. Research in both the semantic coherence of a topic models [2, 3, 4, 5] and measures of model fitness [6] provide strong support that explicitly modeling word dependencies—as in APM—could be both semantically meaningful and essential for appropriately modeling real text data. Though APM shows significant promise for providing a better topic model, APM has a high computational complexity because O(p2) parameters must be estimated where p is the number of words ([1] could only provide results for datasets with p = 200). In light of this, we develop a parallel alternating Newton-like algorithm for training the APM model that can handle p = 104 as an important step towards scaling to large datasets. In addition, Inouye et al. [1] only provided tentative and inconclusive results on the utility of APM. Thus, motivated by simple intuitions and previous evaluations of topic models, we propose a novel evaluation metric based on human evocation scores between word pairs (i.e. how much one word "brings to mind" another word [7]). We provide compelling quantitative and qualitative results on the BNC corpus that demonstrate the superiority of APM over previous topic models for identifying semantically meaningful word dependencies. (MATLAB code available at: http://bigdata.ices.utexas.edu/software/apm/)

/pdf/capturing-semantically-meaningful-word-dependencies-with-an-3yugrndh5j.pdf

Capturing Semantically Meaningful Word Dependencies with an Admixture of Poisson MRFs

Research areas: Machine learning, Data mining, Information visualization, Visual analytics, Text visualization.

/pdf/visirr-interactive-visual-information-retrieval-and-d8t11puu8h.pdf

VisIRR: Interactive Visual Information Retrieval and Recommendation for Large-scale Document Data

A distribution shift can have fundamental consequences such as signaling a change in the operating environment or significantly reducing the accuracy of downstream models. Thus, understanding distribution shifts is critical for examining and hopefully mitigating the effect of such a shift. Most prior work focuses on merely detecting if a shift has occurred and assumes any detected shift can be understood and handled appropriately by a human operator. We hope to aid in these manual mitigation tasks by explaining the distribution shift using interpretable transportation maps from the original distribution to the shifted one. We derive our interpretable mappings from a relaxation of optimal transport, where the candidate mappings are restricted to a set of interpretable mappings. We then inspect multiple quintessential use-cases of distribution shift in real-world tabular, text, and image datasets to showcase how our explanatory mappings provide a better balance between detail and interpretability than baseline explanations by both visual inspection and our PercentExplained metric.

Towards Explaining Distribution Shifts

Shapley values have become one of the most popular feature attribution explanation methods. However, most prior work has focused on post-hoc Shapley explanations, which can be computationally demanding (exponential time complexity) and preclude model regularization based on Shapley explanations during training. Thus, we propose to incorporate Shapley values themselves as latent representations in deep models---thereby making Shapley explanations first-class citizens in the modeling paradigm. This intrinsic explanation approach enables layer-wise explanations, explanation regularization of the model during training, and fast explanation computation at test time. We define the Shapley transform that transforms the input into a Shapley representation given a specific function. We operationalize the Shapley transform as a neural network module and construct both shallow and deep networks, called ShapNets, by composing Shapley modules. We prove that our Shallow ShapNets compute the exact Shapley values and our Deep ShapNets maintain the missingness and accuracy properties of Shapley values. We demonstrate on synthetic and real-world datasets that our ShapNets enable layer-wise Shapley explanations, novel Shapley regularizations during training, and fast computation while maintaining reasonable performance. Code is available at https://www.github.com/RuiWang1998/ShapleyExplanationNetworks.

/pdf/shapley-explanation-networks-192rzybg4e.pdf

Shapley Explanation Networks

We present a novel k-way high-dimensional graphical model called the Generalized Root Model (GRM) that explicitly models dependencies between variable sets of size k > 2---where k = 2 is the standard pairwise graphical model. This model is based on taking the k-th root of the original sufficient statistics of any univariate exponential family with positive sufficient statistics, including the Poisson and exponential distributions. As in the recent work with square root graphical (SQR) models [Inouye et al. 2016]---which was restricted to pairwise dependencies---we give the conditions of the parameters that are needed for normalization using the radial conditionals similar to the pairwise case [Inouye et al. 2016]. In particular, we show that the Poisson GRM has no restrictions on the parameters and the exponential GRM only has a restriction akin to negative definiteness. We develop a simple but general learning algorithm based on L1-regularized node-wise regressions. We also present a general way of numerically approximating the log partition function and associated derivatives of the GRM univariate node conditionals---in contrast to [Inouye et al. 2016], which only provided algorithm for estimating the exponential SQR. To illustrate GRM, we model word counts with a Poisson GRM and show the associated k-sized variable sets. We finish by discussing methods for reducing the parameter space in various situations.

David I. Inouye

Papers

Capturing Semantically Meaningful Word Dependencies with an Admixture of Poisson MRFs

VisIRR: Interactive Visual Information Retrieval and Recommendation for Large-scale Document Data

Towards Explaining Distribution Shifts

Shapley Explanation Networks

Generalized Root Models: Beyond Pairwise Graphical Models for Univariate Exponential Families