Workshop
Human in the Loop Learning (HiLL) Workshop at NeurIPS 2022
Shanghang Zhang · Hao Dong · Wei Pan · Pradeep Ravikumar · Vittorio Ferrari · Fisher Yu · Xin Wang · Zihan Ding
Room 396
Fri 2 Dec, 6:30 a.m. PST
Recent years have witnessed the rising need for machine learning systems that can interact with humans in the learning loop. Such systems can be applied to computer vision, natural language processing, robotics, and human-computer interaction. Creating and running such systems call for interdisciplinary research of artificial intelligence, machine learning, and software engineering design, which we abstract as Human in the Loop Learning (HiLL).
The HiLL workshop aims to bring together researchers and practitioners working on the broad areas of HiLL, ranging from interactive/active learning algorithms for real-world decision-making systems (e.g., autonomous driving vehicles, robotic systems, etc.), human-inspired learning that mitigates the gap between human intelligence and machine intelligence, human-machine collaborative learning that creates a more powerful learning system, lifelong learning that transfers knowledge to learn new tasks over a lifetime, as well as interactive system designs (e.g., data visualization, annotation systems, etc.).
The HiLL workshop continues the previous effort to provide a platform for researchers from interdisciplinary areas to share their recent research. In this year’s workshop, a special feature is to encourage the discussion on the interactive and collaborative learning between human and machine learning agents: Can they be organically combined to create a more powerful learning system? We believe the theme of the workshop will be of interest to broad NeurIPS attendees, especially those who are interested in interdisciplinary study.
Schedule
Fri 6:30 a.m. - 7:00 a.m.
|
Openning Remark
(
Openning Remark
)
>
SlidesLive Video |
🔗 |
Fri 7:00 a.m. - 7:30 a.m.
|
Interactive Imitation Learning in Robotics
(
Invited Talk
)
>
link
SlidesLive Video |
Jens Kober 🔗 |
Fri 7:30 a.m. - 8:00 a.m.
|
What to learn from humans?
(
Invited Talk
)
>
link
SlidesLive Video |
Danica Kragic 🔗 |
Fri 8:00 a.m. - 8:30 a.m.
|
Human in the Loop Learning for Robot Navigation and Task Learning from Implicit Human Feedback
(
Invited Talk
)
>
link
SlidesLive Video |
Peter Stone 🔗 |
Fri 8:30 a.m. - 9:00 a.m.
|
Language models and interactive decision-making
(
Invited Talk
)
>
link
SlidesLive Video |
Igor Mordatch 🔗 |
Fri 9:00 a.m. - 9:30 a.m.
|
Collaborative AI for assisting virtual laboratories
(
invited Talk
)
>
link
SlidesLive Video |
Samuel Kaski 🔗 |
Fri 9:30 a.m. - 10:00 a.m.
|
Let’s Give Domain Experts a Choice by Creating Many Approximately-Optimal Machine Learning Models
(
Invited Talk
)
>
link
SlidesLive Video |
Cynthia Rudin 🔗 |
Fri 10:00 a.m. - 11:00 a.m.
|
Poster
(
Poster
)
>
|
🔗 |
Fri 11:00 a.m. - 11:10 a.m.
|
Human Interventions in Concept Graph Networks
(
Contributed Talk
)
>
SlidesLive Video |
🔗 |
Fri 11:10 a.m. - 11:20 a.m.
|
Nano: Nested Human-in-the-Loop Reward Learning for Controlling Distribution of Generated Text
(
Contributed Talk
)
>
SlidesLive Video |
🔗 |
Fri 11:20 a.m. - 11:30 a.m.
|
Differentiable User Models
(
Contributed Talk
)
>
SlidesLive Video |
🔗 |
Fri 11:30 a.m. - 12:00 p.m.
|
Mixed-Reality Human-in-the-Loop Learning: Opportunities and Challenges
(
Invited Talk
)
>
link
SlidesLive Video |
Dan Bohus 🔗 |
Fri 12:00 p.m. - 12:30 p.m.
|
Human and Machine Learning for Assistive and Rehabilitation Robots
(
Invited Talk
)
>
link
SlidesLive Video |
Brenna Argall 🔗 |
Fri 12:30 p.m. - 1:00 p.m.
|
Aligning Humans and Robots: Active Elicitation of Informative and Compatible Queries
(
Invited Talk
)
>
link
SlidesLive Video |
Dorsa Sadigh 🔗 |
Fri 1:00 p.m. - 1:30 p.m.
|
Imitation, Innovation and Caregiving in Children and AI
(
Invited Talk, with Eunice Yiu
)
>
link
SlidesLive Video |
Alison Gopnik 🔗 |
Fri 1:30 p.m. - 2:00 p.m.
|
Human-Guided Motion Planning in Partially Observable Environments
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Fri 2:00 p.m. - 3:00 p.m.
|
Panel Discussion
(
Panel
)
>
SlidesLive Video |
Cynthia Rudin · Dan Bohus · Brenna Argall · Alison Gopnik · Igor Mordatch · Samuel Kaski 🔗 |
Fri 3:00 p.m. -
|
Poster
(
Poster
)
>
|
🔗 |
-
|
Modeling Semantic Correlation and Hierarchy for Real-world Wildlife Recognition
(
Poster
)
>
|
Dong-Jin Kim · Zhongqi Miao · Yunhui Guo · Stella Yu · Kyle Landolt · Mark Koneff · Travis Harrison 🔗 |
-
|
Making Your First Choice: To Address Cold Start Problem in Vision Active Learning
(
Poster
)
>
|
Liangyu Chen · Yutong Bai · Siyu Huang · Yongyi Lu · Bihan Wen · Alan Yuille · Zongwei Zhou 🔗 |
-
|
Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning
(
Poster
)
>
|
Katherine Metcalf · Miguel Sarabia · Barry-John Theobald 🔗 |
-
|
(When) Are Contrastive Explanations of Reinforcement Learning Helpful?
(
Poster
)
>
|
Sanjana Narayanan · Isaac Lage · Finale Doshi-Velez 🔗 |
-
|
Human Interventions in Concept Graph Networks
(
Poster
)
>
|
Lucie Charlotte Magister · Pietro Barbiero · Dmitry Kazhdan · Federico Siciliano · Gabriele Ciravegna · Fabrizio Silvestri · Mateja Jamnik · Pietro Lió 🔗 |
-
|
Identifying the Context Shift between Test Benchmarks and Production Data
(
Poster
)
>
|
Matt Groh 🔗 |
-
|
Continually Learned Pavlovian Signalling Without Forgetting for Human-in-the-Loop Robotic Control
(
Poster
)
>
|
Adam Parker · Michael Dawson · Patrick M Pilarski 🔗 |
-
|
MultiViz: Towards Visualizing and Understanding Multimodal Models
(
Poster
)
>
|
Paul Pu Liang · · Gunjan Chhablani · Nihal Jain · Zihao Deng · Xingbo Wang · Louis-Philippe Morency · Ruslan Salakhutdinov 🔗 |
-
|
Environment Design for Inverse Reinforcement Learning
(
Poster
)
>
|
Thomas Kleine Buening · Christos Dimitrakakis 🔗 |
-
|
Improving Named Entity Recognition in Telephone Conversations via Effective Active Learning with Human in the Loop
(
Poster
)
>
|
Md Tahmid Rahman Laskar · Cheng Chen · Xue-Yong Fu · Shashi Bhushan 🔗 |
-
|
Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration
(
Poster
)
>
|
Wenhao Li · Chuyun Shen · Qisen Xu · Bin Hu · · Haibin Cai · Fengping Zhu · Yuxin Li · Xiangfeng Wang 🔗 |
-
|
Generating Personalized Counterfactual Interventions for Algorithmic Recourse by Eliciting User Preferences
(
Poster
)
>
|
Giovanni De Toni · Paolo Viappiani · Bruno Lepri · Andrea Passerini 🔗 |
-
|
Description2Font: Font Generation via Style Description
(
Poster
)
>
|
Pan Wang · Xun Zhang · Peter Childs · Kunpyo Lee · Stephen Jia WANG 🔗 |
-
|
Nano: Nested Human-in-the-Loop Reward Learning for Controlling Distribution of Generated Text
(
Poster
)
>
|
Xiang Fan · · Paul Pu Liang · Ruslan Salakhutdinov · Louis-Philippe Morency 🔗 |
-
|
Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learning
(
Poster
)
>
|
Alessandro Sestini · Carl Joakim Bergdahl · Konrad Tollmar · Andrew Bagdanov · Linus Gisslén 🔗 |
-
|
Identifying Spurious Correlations and Correcting them with an Explanation-based Learning
(
Poster
)
>
|
Misgina Tsighe Hagos · Kathleen Curran · Brian Mac Namee 🔗 |
-
|
"I pick you choose": Joint human-algorithm decision making in multi-armed bandits
(
Poster
)
>
|
Kate Donahue · Sreenivas Gollapudi · Kostas Kollias 🔗 |
-
|
Active metric learning and classification using similarity queries
(
Poster
)
>
|
Namrata Nadagouda · Austin Xu · Mark Davenport 🔗 |
-
|
Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models
(
Poster
)
>
|
Yi Liu · Gaurav Datta · Ellen Novoseller · Daniel Brown 🔗 |
-
|
Utilizing supervised models to infer consensus labels and their quality from data with multiple annotators
(
Poster
)
>
|
Hui Wen Goh · Ulyana Tkachenko · Jonas Mueller 🔗 |
-
|
Active-Learning-as-a-Service: An Automatic and Efficient MLOps System for Data-Centric AI
(
Poster
)
>
|
Yizheng Huang · Huaizheng Zhang · Yuanming Li · Chiew Tong Lau · Yang You 🔗 |
-
|
Feasible and Desirable Counterfactual Generation by Preserving Human Defined Constraints
(
Poster
)
>
|
Homayun Afrabandpey · Michael Spranger 🔗 |
-
|
Leveraging Human Features at Test-Time
(
Poster
)
>
|
Isaac Lage · Sonali Parbhoo · Finale Doshi-Velez 🔗 |
-
|
OpenAL: Evaluation and Interpretation of Active Learning Strategies
(
Poster
)
>
|
William JONAS · Alexandre Abraham · Léo Dreyfus-Schmidt 🔗 |
-
|
IAdet: Simplest human-in-the-loop object detection
(
Poster
)
>
|
Franco Marchesoni-Acland 🔗 |
-
|
Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion
(
Poster
)
>
|
Utkarsh Soni · Sarath Sreedharan · Mudit Verma · Lin Guan · Matthew Marquez · Subbarao Kambhampati 🔗 |
-
|
Knowledge-driven Active Learning
(
Poster
)
>
|
Gabriele Ciravegna · Frederic Precioso · Marco Gori 🔗 |
-
|
Minimizing Annotation Effort via Spectral Sampling
(
Poster
)
>
|
Ariadna Quattoni 🔗 |
-
|
Enabling Learning as a Joint Task via Paraphrasing
(
Poster
)
>
|
Pallavi Koppol · Russell Wong · Henny Admoni · Reid Simmons 🔗 |
-
|
Symbol Guided Hindsight Priors for Reward Learning from Human Preferences
(
Poster
)
>
|
Mudit Verma · Katherine Metcalf 🔗 |
-
|
Assistance with large language models
(
Poster
)
>
|
Dmitrii Krasheninnikov · Egor Krasheninnikov · David Krueger 🔗 |
-
|
Mapping of Financial Services datasets using Human-in-the-Loop
(
Poster
)
>
|
SHUBHI ASTHANA · Ruchi Mahindru 🔗 |
-
|
Batch Active Learning from the Perspective of Sparse Approximation
(
Poster
)
>
|
Maohao Shen · Yibo Jacky Zhang · Bowen Jiang · Sanmi Koyejo 🔗 |
-
|
Contextual Visual Feature Learning for Zero-Shot Recognition of Human-Object Interactions
(
Poster
)
>
|
Tsung-Wei Ke · Dong-Jin Kim · Stella Yu · Liang Gou · Liu Ren 🔗 |
-
|
TASSAL: Task-Aware Semi-Supervised Active Learning
(
Poster
)
>
|
Erick Chandra · Ramesh Manuvinakurike · Saurav Sahay · Sahisnu Mazumder · Ranganath Krishnan · Jane Yung-jen Hsu 🔗 |
-
|
Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert Sampling
(
Poster
)
>
|
Ashish Kumar · Ilya Kuzovkin 🔗 |
-
|
Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loop
(
Poster
)
>
|
Mudit Verma · Ayush Kharkwal · Subbarao Kambhampati 🔗 |
-
|
A Simple Framework for Active Learning to Rank
(
Poster
)
>
|
Qingzhong Wang · Haifang Li · Haoyi Xiong · Wen Wang · Jiang Bian · Yu Lu · Shuaiqiang Wang · zhicong cheng · Dawei Yin · Dejing Dou 🔗 |
-
|
Learning from Data through Human-Machine Collaboration
(
Poster
)
>
|
Sara Pido · Pietro Crovari · Pietro Pinoli 🔗 |
-
|
Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions
(
Poster
)
>
|
Chanakya Ekbote · Moksh Jain · Payel Das · Yoshua Bengio 🔗 |
-
|
Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
(
Poster
)
>
|
Lin Guan · Karthik Valmeekam · Subbarao Kambhampati 🔗 |
-
|
Neural-Symbolic Recursive Machine for Systematic Generalization
(
Poster
)
>
|
Qing Li · Yixin Zhu · Yitao Liang · Ying Nian Wu · Song-Chun Zhu · Siyuan Huang 🔗 |
-
|
A Comparative Survey of Deep Active Learning
(
Poster
)
>
|
Xueying Zhan · Qingzhong Wang · Kuan-Hao Huang · Haoyi Xiong · Dejing Dou · Antoni Chan 🔗 |
-
|
Improving the Strength of Human-Like Models in Chess
(
Poster
)
>
|
Saumik Narayanan · Kassa Korley · Chien-Ju Ho · Siddhartha Sen 🔗 |
-
|
Fast Adaptation via Human Diagnosis of Task Distribution Shift
(
Poster
)
>
|
Andi Peng · Mark Ho · Aviv Netanyahu · Julie A Shah · Pulkit Agrawal 🔗 |
-
|
Participatory Systems for Personalized Prediction
(
Poster
)
>
|
Hailey James · Berk Ustun · Chirag Nagpal · Katherine Heller 🔗 |
-
|
Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning
(
Poster
)
>
|
Junwu Xiong 🔗 |
-
|
Can Calibration Improve Sample Prioritization?
(
Poster
)
>
|
Ganesh Tata · Gautham Krishna Gudur · Gopinath Chennupati · Mohammad Emtiyaz Khan 🔗 |
-
|
Conformal Prediction for Resource Prioritisation in Predicting Rare and Dangerous Outcomes
(
Poster
)
>
|
Varun Babbar · Umang Bhatt · Miri Zilka · Adrian Weller 🔗 |
-
|
A Proposal For An Interactive Parliamentary Debate Adjudication System
(
Poster
)
>
|
Priya Pitre · Omkar Joshi 🔗 |
-
|
ArgAnalysis35K - A large scale dataset for Argument Quality Detection
(
Poster
)
>
|
Omkar Joshi · Priya Pitre · Dr. Mrs. Yashodhara V. Haribhakta 🔗 |
-
|
Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations
(
Poster
)
>
|
Felix Yanwei Wang · Nadia Figueroa · Shen Li · Ankit Shah · Julie A Shah 🔗 |
-
|
Exploratory Training: When Trainers Learn
(
Poster
)
>
|
Rajesh Shrestha · Omeed Habibelahian · Arash Termehchy · Papotti Paolo 🔗 |
-
|
Online Continual Learning from Imbalanced Data with Kullback-Leibler-loss based replay buffer updates
(
Poster
)
>
|
Sotirios Nikoloutsopoulos · Iordanis Koutsopoulos · Michalis Titsias 🔗 |
-
|
Interactive Concept Bottleneck Models
(
Poster
)
>
|
Kushal Chauhan · Rishabh Tiwari · Jan Freyberg · Pradeep Shenoy · Krishnamurthy Dvijotham 🔗 |
-
|
Achieving Diversity and Relevancy in Zero-Shot Recommender Systems for Human Evaluations
(
Poster
)
>
|
Tiancheng Yu · Yifei Ma · Anoop Deoras 🔗 |
-
|
Differentiable User Models
(
Poster
)
>
|
Alex Hämäläinen · Mustafa Mert Çelikok · Samuel Kaski 🔗 |
-
|
End-user-centered Interactive Explanatory Relational Learning with Inductive Logic Programming
(
Poster
)
>
|
Oliver Deane 🔗 |
-
|
Time-Efficient Reward Learning via Visually Assisted Cluster Ranking
(
Poster
)
>
|
David Zhang · Micah Carroll · Andreea Bobu · Anca Dragan 🔗 |
-
|
Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration
(
Poster
)
>
|
Mesut Yang · Micah Carroll · Anca Dragan 🔗 |
-
|
Learning Topological Representation of Sensor Network with Persistent Homology in HCI Systems
(
Poster
)
>
|
Yan Yan · Cheng-Dong Li · Jing Xiong · Lei Wang 🔗 |
-
|
On the Ramifications of Human Label Uncertainty
(
Poster
)
>
|
Chen Zhou · Mohit Prabhushankar · Ghassan AlRegib 🔗 |
-
|
A Study of Human-Robot Handover through Human-Human Object Transfer
(
Poster
)
>
|
Charlotte Morissette · Bobak Baghi · Francois Hogan · Gregory Dudek 🔗 |
-
|
PyTAIL - Interactive and Incremental Learning of NLP Models with Human in the Loop for Online Data
(
Poster
)
>
|
Shubhanshu Mishra · Jana Diesner 🔗 |