6^th Workshop on
Visualization for AI Explainability

October 18th, 2023 Online at 8:00am PT / 3:00pm UTC (+ meetup at IEEE VIS 2023 in Melbourne, Australia)

The role of visualization in artificial intelligence (AI) gained significant attention in recent years. With the growing complexity of AI models, the critical need for understanding their inner-workings has increased. Visualization is potentially a powerful technique to fill such a critical need.

The goal of this workshop is to initiate a call for "explainables" / "explorables" that explain how AI techniques work using visualization. We believe the VIS community can leverage their expertise in creating visual narratives to bring new insight into the often obfuscated complexity of AI systems.

Important Dates

July 30, 2023, anywhere: Submission Deadline
September 10, 2023: Author Notification
October 1, 2023: Camera Ready Deadline
October 18th, 2023 at 8:00am PT / 3:00pm UTC: Workshop Online
October xx, 2023: (optional) Meetup in Melbourne at VIS 2023 
    

Program Overview

All times in PT (UTC -8) on Wednesday, October 18, 2023.

→ VISxAI is free to attend! Join us via Zoom: VISxAI 2023 Zoom link.
→ Add VISxAI 2023 to your calendar!
→ If you plan to attend the in-person VISxAI meetup at IEEE VIS (Thursday, October 26 at 12:00pm), please fill out this form.

8:00	Welcome from the Organizers
8:00 -- 8:30	Session I Conformal Prediction: A Visual Introduction -- Mihir Agarwal, Lalit Chandra Routhu, Zeel B Patel, Nipun Batra Understanding and Comparing Multi-Modal Models -- Christina Humer, Vidya Prasad, Marc Streit, Hendrik Strobelt Neighborhood traces: When your neighborhood changes one layer at a time -- Moritz Dück, Johannes Knittel, Hendrik Strobelt, Mennatallah El-Assady Of Deadly Skullcaps and Amethyst Deceivers: Reflections on a Transdisciplinary Study on XAI and Trust -- Andreas Hinterreiter, Christina Humer, Benedikt Leichtmann, Martina Mara, Marc Streit VisForPINNs: Visualization for Understanding Physics Informed Neural Networks -- Viny Saajan Victor, Manuel Ettmüller, Andre Schmeißer, Heike Leitte, Simone Gramsch
8:30 -- 8:45	Break
8:45 -- 9:15	Session II Do Machine Learning Models Memorize or Generalize? -- Adam Pearce, Asma Ghandeharioun, Nada Hussein, Nithum Thain, Martin Wattenberg, Lucas Dixon Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion -- Seongmin Lee, Benjamin Hoover, Hendrik Strobelt, Zijie J. Wang, ShengYun Peng, Austin P Wright, Kevin Li, Haoyang Yang. Haekyu Park, Duen Horng Chau Learning What's in a Name with Graphical Models -- Vu Luong, Justin S Selig Neural Networks: A Visual Introduction -- Jared Wilber PAC Learning Or: Why We Should (and Shouldn't) Trust Machine Learning -- Dylan Cashman
9:15 -- 9:30	Break
9:30 -- 10:30	Keynote: Matthew Conlen - @mathisonian Beyond Notebooks: Computational Tools for Disseminating Research and Ideas Computational notebooks and interactive essays are both powerful mediums for sharing research; however, designers often mistakenly assume that they share similar design goals and constraints. This talk provides a critical examination of the differences between these two formats, highlighting the potential for interactive essays to move beyond the linear notebook format through a survey of influential works in experimental literature, cinema, graphic design, and game design. Recent research aids authors in crafting interactive essays, leveraging a variety of computational techniques including programming language design, structured text editing, computer graphics, and AR/VR.
10:30am	Closing

Call for Participation

Explainable submissions (e.g., interactive articles, markup, and notebooks) are the core element of the workshop, as this workshop aims to be a platform for explanatory visualizations focusing on AI techniques.

Authors have the freedom to use whatever templates and formats they like. However, the narrative has to be visual and interactive, and walk readers through a keen understanding on the ML technique or application. Authors may wish to write a Distill-style blog post (format), interactive Idyll markup, or a Jupyter or Observable notebook that integrates code, text, and visualization to tell the story.

Here are a few examples of visual explanations of AI methods in these types of formats:

• [interactive article] A Visual Exploration of Gaussian Processes
• [interactive article] Why Momentum Really Works
• [interactive article] A Visual Introduction to Machine Learning
• [interactive article] Art-Inspired Data Experiments on Neural Network Model Decay
• [interactive article] Attacking Discrimination with Smarter Machine Learning
• [markup] The Myth of the Impartial Machine
• [markup] The Beginner's Guide to Dimensionality Reduction
• [notebook] t-SNE Explained in Plain JavaScript
• [notebook] How to build a Teachable Machine with TensorFlow.js
• [notebook] Titanic Machine Learning from Disaster

While these examples are informative and excellent, we hope the Visualization & ML community will think about ways to creatively expand on such foundational work to explain AI methods using novel interactions and visualizations often present at IEEE VIS. Please contact us, if you want to submit a original work in another format. Email: orga.visxai (at) gmail.com.

Our workshop will be hybrid. We encourage and accept submissions for those who cannot travel to VIS in person.

Note: We also accept more traditional papers that accompany an explainable. Be aware that we require that the explainable must stand on its own. The reviewers will evaluate the explainable (and might chose to ignore the paper).

Hall of Fame

Each year we award Best Submissions and Honorable Mentions. Congrats to our winners!

VISxAI 2023

• PAC Learning Or: Why We Should (and Shouldn't) Trust Machine Learning -- Dylan Cashman
• Understanding and Comparing Multi-Modal Models -- Christina Humer, Vidya Prasad, Marc Streit, Hendrik Strobelt
• Do Machine Learning Models Memorize or Generalize? -- Adam Pearce, Asma Ghandeharioun, Nada Hussein, Nithum Thain, Martin Wattenberg, Lucas Dixon

VISxAI 2022

• K-Means Clustering: An Explorable Explainer -- Yi Zhe Ang
• Poisoning Attacks and Subpopulation Susceptibility -- Evan Rose, Fnu Suya, David Evans

VISxAI 2021

• What Have Language Models Learned? -- Adam Pearce
• Feature Sonification: An investigation on the features learned for Automatic Speech Recognition -- Amin Ghiasi, Hamid Kazemi, W. Ronny Huang, Emily Liu, Micah Goldblum, Tom Goldstein

VISxAI 2020

• Comparing DNNs with UMAP Tour -- Mingwei Li and Carlos Scheidegger
• How Does a Computer "See" Gender? -- Stefan Wojcik, Emma Remy, and Chris Baronavski

VISxAI 2019

• What if we Reduce the Memory of an Artificial Doom Player? -- Theo Jaunet, Romain Vuillemot, and Christian Wolf
• Statistical Distances and Their Implications to GAN Training -- Max Daniels
• Selecting the right tool for the job: a comparison of visualization algorithms -- Daniel Burkhardt, Scott Gigante, and Smita Krishnaswamy

VISxAI 2018

• A Visual Exploration of Gaussian Processes -- Jochen Görtler, Rebecca Kehlbeck and Oliver Deussen
• The Beginner's Guide to Dimensionality Reduction -- Matthew Conlen and Fred Hohman
• Roads from Above -- Greg More, Slaven Marusic and Caihao Cui

Organizers (alphabetic)

Alex Bäuerle - Independent Researcher
Angie Boggust - Massachusetts Institute of Technology
Fred Hohman - Apple
Ian Johnson - Latent Interfaces
Zijie Jay Wang - Georgia Tech

Steering Committee

Adam Perer - Carnegie Mellon University
Hendrik Strobelt - MIT-IBM Watson AI Lab
Mennatallah El-Assady - ETH AI Center

Program Committee

Jane Adams
Marco Angelini
Donald Bertucci
Ángel Cabrera
Jaegul Choo
Brandon Duderstadt
Angus Forbes
Iris Howley
Andriy Mulyar
Rita Sevastjanova
Arjun Srinivasan
Yang Wang
James Wexler