David I. Inouye

Bio: David I. Inouye is an academic researcher from Purdue University. The author has contributed to research in topics: Poisson distribution & Univariate. The author has an hindex of 9, co-authored 29 publications receiving 494 citations. Previous affiliations of David I. Inouye include Georgia Institute of Technology & University of Texas at Austin.

On the (In)fidelity and Sensitivity of Explanations

Abstract: We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been considered in recent literature: (in)fidelity, and sensitivity. We analyze optimal explanations with respect to both these measures, and while the optimal explanation for sensitivity is a vacuous constant explanation, the optimal explanation for infidelity is a novel combination of two popular explanation methods. By varying the perturbation distribution that defines infidelity, we obtain novel explanations by optimizing infidelity, which we show to out-perform existing explanations in both quantitative and qualitative measurements. Another salient question given these measures is how to modify any given explanation to have better values with respect to these measures. We propose a simple modification based on lowering sensitivity, and moreover show that when done appropriately, we could simultaneously improve both sensitivity as well as fidelity.

Comparing Twitter Summarization Algorithms for Multiple Post Summaries

Abstract: Due to the sheer volume of text generated by a micro log site like Twitter, it is often difficult to fully understand what is being said about various topics. In an attempt to understand micro logs better, this paper compares algorithms for extractive summarization of micro log posts. We present two algorithms that produce summaries by selecting several posts from a given set. We evaluate the generated summaries by comparing them to both manually produced summaries and summaries produced by several leading traditional summarization systems. In order to shed light on the special nature of Twitter posts, we include extensive analysis of our results, some of which are unexpected.

A review of multivariate distributions for count data derived from the Poisson distribution

Abstract: The Poisson distribution has been widely studied and used for modeling univariate count-valued data. However, multivariate generalizations of the Poisson distribution that permit dependencies have been far less popular. Yet, real-world, high-dimensional, count-valued data found in word counts, genomics, and crime statistics, for example, exhibit rich dependencies and motivate the need for multivariate distributions that can appropriately model this data. We review multivariate distributions derived from the univariate Poisson, categorizing these models into three main classes: 1 where the marginal distributions are Poisson, 2 where the joint distribution is a mixture of independent multivariate Poisson distributions, and 3 where the node-conditional distributions are derived from the Poisson. We discuss the development of multiple instances of these classes and compare the models in terms of interpretability and theory. Then, we empirically compare multiple models from each class on three real-world datasets that have varying data characteristics from different domains, namely traffic accident data, biological next generation sequencing data, and text data. These empirical experiments develop intuition about the comparative advantages and disadvantages of each class of multivariate distribution that was derived from the Poisson. Finally, we suggest new research directions as explored in the subsequent Discussion section. WIREs Comput Stat 2017, 9:e1398. doi: 10.1002/wics.1398

Summarization of Twitter Microblogs

Abstract: Owing to the sheer volume of text generated by a microblog site like Twitter, it is often difficult to fully understand what is being said about various topics. This paper presents algorithms for summarizing microblog documents. Initially, we present algorithms that produce single-document summaries but later extend them to produce summaries containing multiple documents. We evaluate the generated summaries by comparing them to both manually produced summaries and, for the multiple-post summaries, to the summarization results of some of the leading traditional summarization systems.

Admixture of Poisson MRFs: A Topic Model with Word Dependencies

Abstract: This paper introduces a new topic model based on an admixture of Poisson Markov Random Fields (APM), which can model dependencies between words as opposed to previous independent topic models such as PLSA (Hofmann, 1999), LDA (Blei et al., 2003) or SAM (Reisinger et al., 2010). We propose a class of admixture models that generalizes previous topic models and show an equivalence between the conditional distribution of LDA and independent Poissons--suggesting that APM subsumes the modeling power of LDA. We present a tractable method for estimating the parameters of an APM based on the pseudo log-likelihood and demonstrate the benefits of APM over previous models by preliminary qualitative and quantitative experiments.

Normalizing Flows for Probabilistic Modeling and Inference

Abstract: 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.

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

Abstract: 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.

Text Summarization Techniques: A Brief Survey

Abstract: 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.