Fred Hohman

Zijie J. Wang, Fred Hohman, Duen Horng Chau · apple-ml, gatech

Machine learning models often learn latent embedding representations that capture the domain semantics of their training data. These embedding representations are valuable for interpreting trained models, building new models, and analyzing new datasets. However, interpreting and using embeddings can be challenging due to their opaqueness, high dimensionality, and the large size of modern datasets. To tackle these challenges, we present WizMap, an interactive visualization tool to help researchers and practitioners easily explore large embeddings. With a novel multi-resolution embedding summarization method and a familiar map-like interaction design, WizMap enables users to navigate and interpret embedding spaces with ease. Leveraging modern web technologies such as WebGL and Web Workers, WizMap scales to millions of embedding points directly in users' web browsers and computational notebooks without the need for dedicated backend servers. WizMap is open-source and available at the following public demo link: https://poloclub.github.io/wizmap.

Fred Hohman, Mary Beth Kery, Donghao Ren et al. · apple-ml, cmu

On-device machine learning (ML) promises to improve the privacy, responsiveness, and proliferation of new, intelligent user experiences by moving ML computation onto everyday personal devices. However, today's large ML models must be drastically compressed to run efficiently on-device, a hurtle that requires deep, yet currently niche expertise. To engage the broader human-centered ML community in on-device ML experiences, we present the results from an interview study with 30 experts at Apple that specialize in producing efficient models. We compile tacit knowledge that experts have developed through practical experience with model compression across different hardware platforms. Our findings offer pragmatic considerations missing from prior work, covering the design process, trade-offs, and technical strategies that go into creating efficient models. Finally, we distill design recommendations for tooling to help ease the difficulty of this work and bring on-device ML into to more widespread practice.

Samantha Robertson, Zijie J. Wang, Dominik Moritz et al. · apple-ml, cmu

Machine learning (ML) models can fail in unexpected ways in the real world, but not all model failures are equal. With finite time and resources, ML practitioners are forced to prioritize their model debugging and improvement efforts. Through interviews with 13 ML practitioners at Apple, we found that practitioners construct small targeted test sets to estimate an error's nature, scope, and impact on users. We built on this insight in a case study with machine translation models, and developed Angler, an interactive visual analytics tool to help practitioners prioritize model improvements. In a user study with 7 machine translation experts, we used Angler to understand prioritization practices when the input space is infinite, and obtaining reliable signals of model quality is expensive. Our study revealed that participants could form more interesting and user-focused hypotheses for prioritization by analyzing quantitative summary statistics and qualitatively assessing data by reading sentences.

Angie Boggust, Venkatesh Sivaraman, Yannick Assogba et al. · apple-ml, cmu

To deploy machine learning models on-device, practitioners use compression algorithms to shrink and speed up models while maintaining their high-quality output. A critical aspect of compression in practice is model comparison, including tracking many compression experiments, identifying subtle changes in model behavior, and negotiating complex accuracy-efficiency trade-offs. However, existing compression tools poorly support comparison, leading to tedious and, sometimes, incomplete analyses spread across disjoint tools. To support real-world comparative workflows, we develop an interactive visual system called Compress and Compare. Within a single interface, Compress and Compare surfaces promising compression strategies by visualizing provenance relationships between compressed models and reveals compression-induced behavior changes by comparing models' predictions, weights, and activations. We demonstrate how Compress and Compare supports common compression analysis tasks through two case studies, debugging failed compression on generative language models and identifying compression artifacts in image classification models. We further evaluate Compress and Compare in a user study with eight compression experts, illustrating its potential to provide structure to compression workflows, help practitioners build intuition about compression, and encourage thorough analysis of compression's effect on model behavior. Through these evaluations, we identify compression-specific challenges that future visual analytics tools should consider and Compress and Compare visualizations that may generalize to broader model comparison tasks.

Aspen Hopkins, Fred Hohman, Luca Zappella et al. · apple-ml, cmu

Lack of diversity in data collection has caused significant failures in machine learning (ML) applications. While ML developers perform post-collection interventions, these are time intensive and rarely comprehensive. Thus, new methods to track & manage data collection, iteration, and model training are necessary for evaluating whether datasets reflect real world variability. We present designing data, an iterative approach to data collection connecting HCI concepts with ML techniques. Our process includes (1) Pre-Collection Planning, to reflexively prompt and document expected data distributions; (2) Collection Monitoring, to systematically encourage sampling diversity; and (3) Data Familiarity, to identify samples that are unfamiliar to a model using density estimation. We apply designing data to a data collection and modeling task. We find models trained on ''designed'' datasets generalize better across intersectional groups than those trained on similarly sized but less targeted datasets, and that data familiarity is effective for debugging datasets.

Michelle S. Lam, Fred Hohman, Dominik Moritz et al. · apple-ml, cmu

AI policy sets boundaries on acceptable behavior for AI models, but this is challenging in the context of large language models (LLMs): how do you ensure coverage over a vast behavior space? We introduce policy maps, an approach to AI policy design inspired by the practice of physical mapmaking. Instead of aiming for full coverage, policy maps aid effective navigation through intentional design choices about which aspects to capture and which to abstract away. With Policy Projector, an interactive tool for designing LLM policy maps, an AI practitioner can survey the landscape of model input-output pairs, define custom regions (e.g., "violence"), and navigate these regions with if-then policy rules that can act on LLM outputs (e.g., if output contains "violence" and "graphic details," then rewrite without "graphic details"). Policy Projector supports interactive policy authoring using LLM classification and steering and a map visualization reflecting the AI practitioner's work. In an evaluation with 12 AI safety experts, our system helps policy designers craft policies around problematic model behaviors such as incorrect gender assumptions and handling of immediate physical safety threats.

Tiffany Tseng, Jennifer King Chen, Mona Abdelrahman et al. · apple-ml, uw

Existing novice-friendly machine learning (ML) modeling tools center around a solo user experience, where a single user collects only their own data to build a model. However, solo modeling experiences limit valuable opportunities for encountering alternative ideas and approaches that can arise when learners work together; consequently, it often precludes encountering critical issues in ML around data representation and diversity that can surface when different perspectives are manifested in a group-constructed data set. To address this issue, we created Co-ML -- a tablet-based app for learners to collaboratively build ML image classifiers through an end-to-end, iterative model-building process. In this paper, we illustrate the feasibility and potential richness of collaborative modeling by presenting an in-depth case study of a family (two children 11 and 14-years-old working with their parents) using Co-ML in a facilitated introductory ML activity at home. We share the Co-ML system design and contribute a discussion of how using Co-ML in a collaborative activity enabled beginners to collectively engage with dataset design considerations underrepresented in prior work such as data diversity, class imbalance, and data quality. We discuss how a distributed collaborative process, in which individuals can take on different model-building responsibilities, provides a rich context for children and adults to learn ML dataset design.

Tom Gunter, Zirui Wang, Chong Wang et al.

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

Donghao Ren, Fred Hohman, Halden Lin et al. · apple-ml, cmu

Embedding projections are popular for visualizing large datasets and models. However, people often encounter "friction" when using embedding visualization tools: (1) barriers to adoption, e.g., tedious data wrangling and loading, scalability limits, no integration of results into existing workflows, and (2) limitations in possible analyses, without integration with external tools to additionally show coordinated views of metadata. In this paper, we present Embedding Atlas, a scalable, interactive visualization tool designed to make interacting with large embeddings as easy as possible. Embedding Atlas uses modern web technologies and advanced algorithms -- including density-based clustering, and automated labeling -- to provide a fast and rich data analysis experience at scale. We evaluate Embedding Atlas with a competitive analysis against other popular embedding tools, showing that Embedding Atlas's feature set specifically helps reduce friction, and report a benchmark on its real-time rendering performance with millions of points. Embedding Atlas is available as open source to support future work in embedding-based analysis.

Alex Oesterling, Donghao Ren, Yannick Assogba et al.

Safety policies define what constitutes safe and unsafe AI outputs, guiding data annotation and model development. However, annotation disagreement is pervasive and can stem from multiple sources such as operational failures (annotators misunderstand or misexecute the task), policy ambiguity (policy wording leaves room for interpretation), or value pluralism (different annotators hold different perspectives on safety). Distinguishing these sources matters. For example, operational failures call for quality control, ambiguity calls for policy clarification, and pluralism calls for deliberation about incorporating diverse perspectives. Yet understanding why annotators disagree is difficult. Directly asking annotators for their reasoning is costly, substantially increasing annotation burden, and can be unreliable for both human and LLM annotators as self-reported reasoning often fails to reflect actual decision processes. We introduce Annotator Policy Models (APMs), interpretable models that learn annotators' internal safety policies from labeling behavior alone, making annotator reasoning visible and comparable without additional annotation effort. We validate that APMs accurately model annotator safety policy (>80% accuracy), faithfully predict responses to counterfactual edits, and recover known policy differences in controlled settings. Applying APMs to LLM and human annotations, we demonstrate two core applications: (1) surfacing policy ambiguity by revealing how annotators interpret safety instructions differently, and (2) surfacing value pluralism by uncovering systematic differences in safety priorities across demographic groups. Together, these capabilities support more targeted, transparent, and inclusive safety policy design.

Haekyu Park, Nilaksh Das, Rahul Duggal et al.

Existing research on making sense of deep neural networks often focuses on neuron-level interpretation, which may not adequately capture the bigger picture of how concepts are collectively encoded by multiple neurons. We present NeuroCartography, an interactive system that scalably summarizes and visualizes concepts learned by neural networks. It automatically discovers and groups neurons that detect the same concepts, and describes how such neuron groups interact to form higher-level concepts and the subsequent predictions. NeuroCartography introduces two scalable summarization techniques: (1) neuron clustering groups neurons based on the semantic similarity of the concepts detected by neurons (e.g., neurons detecting "dog faces" of different breeds are grouped); and (2) neuron embedding encodes the associations between related concepts based on how often they co-occur (e.g., neurons detecting "dog face" and "dog tail" are placed closer in the embedding space). Key to our scalable techniques is the ability to efficiently compute all neuron pairs' relationships, in time linear to the number of neurons instead of quadratic time. NeuroCartography scales to large data, such as the ImageNet dataset with 1.2M images. The system's tightly coordinated views integrate the scalable techniques to visualize the concepts and their relationships, projecting the concept associations to a 2D space in Neuron Projection View, and summarizing neuron clusters and their relationships in Graph View. Through a large-scale human evaluation, we demonstrate that our technique discovers neuron groups that represent coherent, human-meaningful concepts. And through usage scenarios, we describe how our approaches enable interesting and surprising discoveries, such as concept cascades of related and isolated concepts. The NeuroCartography visualization runs in modern browsers and is open-sourced.

Nilaksh Das, Haekyu Park, Zijie J. Wang et al.

Deep neural networks (DNNs) are now commonly used in many domains. However, they are vulnerable to adversarial attacks: carefully crafted perturbations on data inputs that can fool a model into making incorrect predictions. Despite significant research on developing DNN attack and defense techniques, people still lack an understanding of how such attacks penetrate a model's internals. We present Bluff, an interactive system for visualizing, characterizing, and deciphering adversarial attacks on vision-based neural networks. Bluff allows people to flexibly visualize and compare the activation pathways for benign and attacked images, revealing mechanisms that adversarial attacks employ to inflict harm on a model. Bluff is open-sourced and runs in modern web browsers.

Fred Hohman, Haekyu Park, Caleb Robinson et al.

Deep learning is increasingly used in decision-making tasks. However, understanding how neural networks produce final predictions remains a fundamental challenge. Existing work on interpreting neural network predictions for images often focuses on explaining predictions for single images or neurons. As predictions are often computed from millions of weights that are optimized over millions of images, such explanations can easily miss a bigger picture. We present Summit, an interactive system that scalably and systematically summarizes and visualizes what features a deep learning model has learned and how those features interact to make predictions. Summit introduces two new scalable summarization techniques: (1) activation aggregation discovers important neurons, and (2) neuron-influence aggregation identifies relationships among such neurons. Summit combines these techniques to create the novel attribution graph that reveals and summarizes crucial neuron associations and substructures that contribute to a model's outcomes. Summit scales to large data, such as the ImageNet dataset with 1.2M images, and leverages neural network feature visualization and dataset examples to help users distill large, complex neural network models into compact, interactive visualizations. We present neural network exploration scenarios where Summit helps us discover multiple surprising insights into a prevalent, large-scale image classifier's learned representations and informs future neural network architecture design. The Summit visualization runs in modern web browsers and is open-sourced.

Ángel Alexander Cabrera, Fred Hohman, Jason Lin et al.

We present an interactive system enabling users to manipulate images to explore the robustness and sensitivity of deep learning image classifiers. Using modern web technologies to run in-browser inference, users can remove image features using inpainting algorithms and obtain new classifications in real time, which allows them to ask a variety of "what if" questions by experimentally modifying images and seeing how the model reacts. Our system allows users to compare and contrast what image regions humans and machine learning models use for classification, revealing a wide range of surprising results ranging from spectacular failures (e.g., a "water bottle" image becomes a "concert" when removing a person) to impressive resilience (e.g., a "baseball player" image remains correctly classified even without a glove or base). We demonstrate our system at The 2018 Conference on Computer Vision and Pattern Recognition (CVPR) for the audience to try it live. Our system is open-sourced at https://github.com/poloclub/interactive-classification. A video demo is available at https://youtu.be/llub5GcOF6w.

Ruijia Cheng, Titus Barik, Alan Leung et al.

Programmers frequently engage with machine learning tutorials in computational notebooks and have been adopting code generation technologies based on large language models (LLMs). However, they encounter difficulties in understanding and working with code produced by LLMs. To mitigate these challenges, we introduce a novel workflow into computational notebooks that augments LLM-based code generation with an additional ephemeral UI step, offering users UI scaffolds as an intermediate stage between user prompts and code generation. We present this workflow in BISCUIT, an extension for JupyterLab that provides users with ephemeral UIs generated by LLMs based on the context of their code and intentions, scaffolding users to understand, guide, and explore with LLM-generated code. Through a user study where 10 novices used BISCUIT for machine learning tutorials, we found that BISCUIT offers users representations of code to aid their understanding, reduces the complexity of prompt engineering, and creates a playground for users to explore different variables and iterate on their ideas.

Fred Hohman, Chaoqun Wang, Jinmook Lee et al. · apple-ml, cmu

On-device machine learning (ML) moves computation from the cloud to personal devices, protecting user privacy and enabling intelligent user experiences. However, fitting models on devices with limited resources presents a major technical challenge: practitioners need to optimize models and balance hardware metrics such as model size, latency, and power. To help practitioners create efficient ML models, we designed and developed Talaria: a model visualization and optimization system. Talaria enables practitioners to compile models to hardware, interactively visualize model statistics, and simulate optimizations to test the impact on inference metrics. Since its internal deployment two years ago, we have evaluated Talaria using three methodologies: (1) a log analysis highlighting its growth of 800+ practitioners submitting 3,600+ models; (2) a usability survey with 26 users assessing the utility of 20 Talaria features; and (3) a qualitative interview with the 7 most active users about their experience using Talaria.

Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang et al. · apple-ml, cmu

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transformer that combines track parallelism, mixture-of-experts sparse computation, and interleaved global-local attention to deliver high quality with competitive cost on Apple's Private Cloud Compute platform. Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling, licensed corpora, and high-quality synthetic data, then further refined with supervised fine-tuning and reinforcement learning on a new asynchronous platform. The resulting models support several additional languages while understanding images and executing tool calls. In public benchmarks and human evaluations, both the server model and the on-device model match or surpass comparably sized open baselines. A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning, allowing developers to integrate these capabilities with a few lines of code. The latest advancements in Apple Intelligence models are grounded in our Responsible AI approach with safeguards like content filtering and locale-specific evaluation, as well as our commitment to protecting our users' privacy with innovations like Private Cloud Compute.

Donghao Ren, Fred Hohman, Dominik Moritz · apple-ml, cmu

Interactive visualization of embedding projections is a useful technique for understanding data and evaluating machine learning models. Labeling data within these visualizations is critical for interpretation, as labels provide an overview of the projection and guide user navigation. However, most methods for producing labels require clustering the points, which can be computationally expensive as the number of points grows. In this paper, we describe an efficient clustering approach using kernel density estimation in the projected 2D space instead of points. This algorithm can produce high-quality cluster regions from a 2D density map in a few hundred milliseconds, orders of magnitude faster than current approaches. We contribute the design of the algorithm, benchmarks, and applications that demonstrate the utility of the algorithm, including labeling and summarization.

Angie Boggust, Donghao Ren, Yannick Assogba et al. · apple-ml, cmu

Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, these natural language feature descriptions are often vague, inconsistent, and require manual relabeling. In response, we introduce semantic regexes, structured language descriptions of LLM features. By combining primitives that capture linguistic and semantic feature patterns with modifiers for contextualization, composition, and quantification, semantic regexes produce precise and expressive feature descriptions. Across quantitative benchmarks and qualitative analyses, we find that semantic regexes match the accuracy of natural language while yielding more concise and consistent feature descriptions. Moreover, their inherent structure affords new types of analyses, including quantifying feature complexity across layers, scaling automated interpretability from insights into individual features to model-wide patterns. Finally, in user studies, we find that semantic regex descriptions help people build accurate mental models of LLM feature activations.

Alex Bäuerle, Ángel Alexander Cabrera, Fred Hohman et al.

Interfaces for machine learning (ML), information and visualizations about models or data, can help practitioners build robust and responsible ML systems. Despite their benefits, recent studies of ML teams and our interviews with practitioners (n=9) showed that ML interfaces have limited adoption in practice. While existing ML interfaces are effective for specific tasks, they are not designed to be reused, explored, and shared by multiple stakeholders in cross-functional teams. To enable analysis and communication between different ML practitioners, we designed and implemented Symphony, a framework for composing interactive ML interfaces with task-specific, data-driven components that can be used across platforms such as computational notebooks and web dashboards. We developed Symphony through participatory design sessions with 10 teams (n=31), and discuss our findings from deploying Symphony to 3 production ML projects at Apple. Symphony helped ML practitioners discover previously unknown issues like data duplicates and blind spots in models while enabling them to share insights with other stakeholders.

Jochen Görtler, Fred Hohman, Dominik Moritz et al.

The confusion matrix, a ubiquitous visualization for helping people evaluate machine learning models, is a tabular layout that compares predicted class labels against actual class labels over all data instances. We conduct formative research with machine learning practitioners at Apple and find that conventional confusion matrices do not support more complex data-structures found in modern-day applications, such as hierarchical and multi-output labels. To express such variations of confusion matrices, we design an algebra that models confusion matrices as probability distributions. Based on this algebra, we develop Neo, a visual analytics system that enables practitioners to flexibly author and interact with hierarchical and multi-output confusion matrices, visualize derived metrics, renormalize confusions, and share matrix specifications. Finally, we demonstrate Neo's utility with three model evaluation scenarios that help people better understand model performance and reveal hidden confusions.

Mary Beth Kery, Donghao Ren, Fred Hohman et al.

We aim to increase the flexibility at which a data worker can choose the right tool for the job, regardless of whether the tool is a code library or an interactive graphical user interface (GUI). To achieve this flexibility, we extend computational notebooks with a new API mage, which supports tools that can represent themselves as both code and GUI as needed. We discuss the design of mage as well as design opportunities in the space of flexible code/GUI tools for data work. To understand tooling needs, we conduct a study with nine professional practitioners and elicit their feedback on mage and potential areas for flexible code/GUI tooling. We then implement six client tools for mage that illustrate the main themes of our study findings. Finally, we discuss open challenges in providing flexible code/GUI interactions for data workers.

Zijie J. Wang, Robert Turko, Omar Shaikh et al.

Deep learning's great success motivates many practitioners and students to learn about this exciting technology. However, it is often challenging for beginners to take their first step due to the complexity of understanding and applying deep learning. We present CNN Explainer, an interactive visualization tool designed for non-experts to learn and examine convolutional neural networks (CNNs), a foundational deep learning model architecture. Our tool addresses key challenges that novices face while learning about CNNs, which we identify from interviews with instructors and a survey with past students. CNN Explainer tightly integrates a model overview that summarizes a CNN's structure, and on-demand, dynamic visual explanation views that help users understand the underlying components of CNNs. Through smooth transitions across levels of abstraction, our tool enables users to inspect the interplay between low-level mathematical operations and high-level model structures. A qualitative user study shows that CNN Explainer helps users more easily understand the inner workings of CNNs, and is engaging and enjoyable to use. We also derive design lessons from our study. Developed using modern web technologies, CNN Explainer runs locally in users' web browsers without the need for installation or specialized hardware, broadening the public's education access to modern deep learning techniques.

Nilaksh Das, Haekyu Park, Zijie J. Wang et al.

Deep neural networks (DNNs) are increasingly powering high-stakes applications such as autonomous cars and healthcare; however, DNNs are often treated as "black boxes" in such applications. Recent research has also revealed that DNNs are highly vulnerable to adversarial attacks, raising serious concerns over deploying DNNs in the real world. To overcome these deficiencies, we are developing Massif, an interactive tool for deciphering adversarial attacks. Massif identifies and interactively visualizes neurons and their connections inside a DNN that are strongly activated or suppressed by an adversarial attack. Massif provides both a high-level, interpretable overview of the effect of an attack on a DNN, and a low-level, detailed description of the affected neurons. These tightly coupled views in Massif help people better understand which input features are most vulnerable or important for correct predictions.

Zijie J. Wang, Robert Turko, Omar Shaikh et al.

The success of deep learning solving previously-thought hard problems has inspired many non-experts to learn and understand this exciting technology. However, it is often challenging for learners to take the first steps due to the complexity of deep learning models. We present our ongoing work, CNN 101, an interactive visualization system for explaining and teaching convolutional neural networks. Through tightly integrated interactive views, CNN 101 offers both overview and detailed descriptions of how a model works. Built using modern web technologies, CNN 101 runs locally in users' web browsers without requiring specialized hardware, broadening the public's education access to modern deep learning techniques.

Xiangyun Lei, Fred Hohman, Duen Horng Chau et al.

In recent years, machine learning (ML) has gained significant popularity in the field of chemical informatics and electronic structure theory. These techniques often require researchers to engineer abstract "features" that encode chemical concepts into a mathematical form compatible with the input to machine-learning models. However, there is no existing tool to connect these abstract features back to the actual chemical system, making it difficult to diagnose failures and to build intuition about the meaning of the features. We present ElectroLens, a new visualization tool for high-dimensional spatially-resolved features to tackle this problem. The tool visualizes high-dimensional data sets for atomistic and electron environment features by a series of linked 3D views and 2D plots. The tool is able to connect different derived features and their corresponding regions in 3D via interactive selection. It is built to be scalable, and integrate with existing infrastructure.

Haekyu Park, Fred Hohman, Duen Horng Chau

As deep neural networks are increasingly used in solving high-stake problems, there is a pressing need to understand their internal decision mechanisms. Visualization has helped address this problem by assisting with interpreting complex deep neural networks. However, current tools often support only single data instances, or visualize layers in isolation. We present NeuralDivergence, an interactive visualization system that uses activation distributions as a high-level summary of what a model has learned. NeuralDivergence enables users to interactively summarize and compare activation distributions across layers, classes, and instances (e.g., pairs of adversarial attacked and benign images), helping them gain better understanding of neural network models.

Ángel Alexander Cabrera, Will Epperson, Fred Hohman et al.

The growing capability and accessibility of machine learning has led to its application to many real-world domains and data about people. Despite the benefits algorithmic systems may bring, models can reflect, inject, or exacerbate implicit and explicit societal biases into their outputs, disadvantaging certain demographic subgroups. Discovering which biases a machine learning model has introduced is a great challenge, due to the numerous definitions of fairness and the large number of potentially impacted subgroups. We present FairVis, a mixed-initiative visual analytics system that integrates a novel subgroup discovery technique for users to audit the fairness of machine learning models. Through FairVis, users can apply domain knowledge to generate and investigate known subgroups, and explore suggested and similar subgroups. FairVis' coordinated views enable users to explore a high-level overview of subgroup performance and subsequently drill down into detailed investigation of specific subgroups. We show how FairVis helps to discover biases in two real datasets used in predicting income and recidivism. As a visual analytics system devoted to discovering bias in machine learning, FairVis demonstrates how interactive visualization may help data scientists and the general public understand and create more equitable algorithmic systems.

James Abello, Fred Hohman, Varun Bezzam et al.

We are developing an interactive graph exploration system called Graph Playground for making sense of large graphs. Graph Playground offers a fast and scalable edge decomposition algorithm, based on iterative vertex-edge peeling, to decompose million-edge graphs in seconds. Graph Playground introduces a novel graph exploration approach and a 3D representation framework that simultaneously reveals (1) peculiar subgraph structure discovered through the decomposition's layers, (e.g., quasi-cliques), and (2) possible vertex roles in linking such subgraph patterns across layers.

Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen et al.

The rapidly growing body of research in adversarial machine learning has demonstrated that deep neural networks (DNNs) are highly vulnerable to adversarially generated images. This underscores the urgent need for practical defense that can be readily deployed to combat attacks in real-time. Observing that many attack strategies aim to perturb image pixels in ways that are visually imperceptible, we place JPEG compression at the core of our proposed Shield defense framework, utilizing its capability to effectively "compress away" such pixel manipulation. To immunize a DNN model from artifacts introduced by compression, Shield "vaccinates" a model by re-training it with compressed images, where different compression levels are applied to generate multiple vaccinated models that are ultimately used together in an ensemble defense. On top of that, Shield adds an additional layer of protection by employing randomization at test time that compresses different regions of an image using random compression levels, making it harder for an adversary to estimate the transformation performed. This novel combination of vaccination, ensembling, and randomization makes Shield a fortified multi-pronged protection. We conducted extensive, large-scale experiments using the ImageNet dataset, and show that our approaches eliminate up to 94% of black-box attacks and 98% of gray-box attacks delivered by the recent, strongest attacks, such as Carlini-Wagner's L2 and DeepFool. Our approaches are fast and work without requiring knowledge about the model.

Fred Hohman, Minsuk Kahng, Robert Pienta et al.

Deep learning has recently seen rapid development and received significant attention due to its state-of-the-art performance on previously-thought hard problems. However, because of the internal complexity and nonlinear structure of deep neural networks, the underlying decision making processes for why these models are achieving such performance are challenging and sometimes mystifying to interpret. As deep learning spreads across domains, it is of paramount importance that we equip users of deep learning with tools for understanding when a model works correctly, when it fails, and ultimately how to improve its performance. Standardized toolkits for building neural networks have helped democratize deep learning; visual analytics systems have now been developed to support model explanation, interpretation, debugging, and improvement. We present a survey of the role of visual analytics in deep learning research, which highlights its short yet impactful history and thoroughly summarizes the state-of-the-art using a human-centered interrogative framework, focusing on the Five W's and How (Why, Who, What, How, When, and Where). We conclude by highlighting research directions and open research problems. This survey helps researchers and practitioners in both visual analytics and deep learning to quickly learn key aspects of this young and rapidly growing body of research, whose impact spans a diverse range of domains.

Caleb Robinson, Fred Hohman, Bistra Dilkina

Knowing where people live is a fundamental component of many decision making processes such as urban development, infectious disease containment, evacuation planning, risk management, conservation planning, and more. While bottom-up, survey driven censuses can provide a comprehensive view into the population landscape of a country, they are expensive to realize, are infrequently performed, and only provide population counts over broad areas. Population disaggregation techniques and population projection methods individually address these shortcomings, but also have shortcomings of their own. To jointly answer the questions of "where do people live" and "how many people live there," we propose a deep learning model for creating high-resolution population estimations from satellite imagery. Specifically, we train convolutional neural networks to predict population in the USA at a $0.01^{\circ} \times 0.01^{\circ}$ resolution grid from 1-year composite Landsat imagery. We validate these models in two ways: quantitatively, by comparing our model's grid cell estimates aggregated at a county-level to several US Census county-level population projections, and qualitatively, by directly interpreting the model's predictions in terms of the satellite image inputs. We find that aggregating our model's estimates gives comparable results to the Census county-level population projections and that the predictions made by our model can be directly interpreted, which give it advantages over traditional population disaggregation methods. In general, our model is an example of how machine learning techniques can be an effective tool for extracting information from inherently unstructured, remotely sensed data to provide effective solutions to social problems.

Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen et al.

Deep neural networks (DNNs) have achieved great success in solving a variety of machine learning (ML) problems, especially in the domain of image recognition. However, recent research showed that DNNs can be highly vulnerable to adversarially generated instances, which look seemingly normal to human observers, but completely confuse DNNs. These adversarial samples are crafted by adding small perturbations to normal, benign images. Such perturbations, while imperceptible to the human eye, are picked up by DNNs and cause them to misclassify the manipulated instances with high confidence. In this work, we explore and demonstrate how systematic JPEG compression can work as an effective pre-processing step in the classification pipeline to counter adversarial attacks and dramatically reduce their effects (e.g., Fast Gradient Sign Method, DeepFool). An important component of JPEG compression is its ability to remove high frequency signal components, inside square blocks of an image. Such an operation is equivalent to selective blurring of the image, helping remove additive perturbations. Further, we propose an ensemble-based technique that can be constructed quickly from a given well-performing DNN, and empirically show how such an ensemble that leverages JPEG compression can protect a model from multiple types of adversarial attacks, without requiring knowledge about the model.