AAAI

Predicting Hyperkalemia in the ICU and Evaluation of Generalizability and Interpretability

Gloria Hyunjung Kwak, Christina Chen, Lowell Ling, Erina Ghosh, Leo Anthony Celi, Pan Hui

Comments 6 pages, 3 figures, 3 tables

Journal ref AAAI 2021 Workshop: Trustworthy AI for Healthcare

Bayes Meets Entailment and Prediction: Commonsense Reasoning with Non-monotonicity, Paraconsistency and Predictive Accuracy

Hiroyuki Kido, Keishi Okamoto

Comments This paper was submitted to AAAI 2021 and rejected

SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning

Ting Yao, Yiheng Zhang, Zhaofan Qiu, Yingwei Pan, Tao Mei

Comments AAAI 2021; Code is publicly available at: https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning

Fair Division of Mixed Divisible and Indivisible Goods

Xiaohui Bei, Zihao Li, Jinyan Liu, Shengxin Liu, Xinhang Lu

Comments Appears in the 34th AAAI Conference on Artificial Intelligence (AAAI), 2020

Journal ref Artificial Intelligence, 293:103436 (2021)

Impact of Explanation on Trust of a Novel Mobile Robot

Stephanie Rosenthal, Elizabeth J. Carter

Comments 9 pages, 3 figures

Journal ref Proceedings of the AAAI Fall Symposium Series - Artificial Intelligence for Human-Robot Interaction: Trust Explainability in Artificial Intelligence for Human-Robot Interaction AI-HRI (AI-HRI '20), November 13-14, 2020, Washington DC, USA

SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models

Haekyu Park, Zijie J. Wang, Nilaksh Das, Anindya S. Paul, Pruthvi Perumalla, Zhiyan Zhou, Duen Horng Chau

Comments Accepted at AAAI'21 Demo

Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecasting

Nam Nguyen, Brian Quanz

Comments Accepted at AAAI 2021 (main conference)

ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces

Zecheng He, Srinivas Sunkara, Xiaoxue Zang, Ying Xu, Lijuan Liu, Nevan Wichers, Gabriel Schubiner, Ruby Lee, Jindong Chen, Blaise Agüera y Arcas

Comments Accepted to AAAI Conference on Artificial Intelligence (AAAI-21)

Deep Epidemiological Modeling by Black-box Knowledge Distillation: An Accurate Deep Learning Model for COVID-19

Dongdong Wang, Shunpu Zhang, Liqiang Wang

Comments Accepted by AAAI-21/IAAI-21, 7 pages, 2 figures

Measuring Dependence with Matrix-based Entropy Functional

Shujian Yu, Francesco Alesiani, Xi Yu, Robert Jenssen, Jose C. Principe

Comments Accepted at AAAI-21. An interpretable and differentiable dependence (or independence) measure that can be used to 1) train deep network under covariate shift and non-Gaussian noise; 2) implement a deep deterministic information bottleneck; and 3) understand the dynamics of learning of CNN. Code available at https://bit.ly/AAAI-dependence

High-Confidence Off-Policy (or Counterfactual) Variance Estimation

Yash Chandak, Shiv Shankar, Philip S. Thomas

Comments Thirty-fifth AAAI Conference on Artificial Intelligence (AAAI 2021)

DocParser: Hierarchical Structure Parsing of Document Renderings

Johannes Rausch, Octavio Martinez, Fabian Bissig, Ce Zhang, Stefan Feuerriegel

Comments AAAI 2021

Neural Relational Inference with Efficient Message Passing Mechanisms

Siyuan Chen, Jiahai Wang, Guoqing Li

Comments Accepted by AAAI 2021, 13 pages, 9 figures, 4 tables

i-Algebra: Towards Interactive Interpretability of Deep Neural Networks

Xinyang Zhang, Ren Pang, Shouling Ji, Fenglong Ma, Ting Wang

Comments Accepted by the 35th AAAI Conference on Artificial Intelligence (AAAI '21)

A Generalization of Transformer Networks to Graphs

Vijay Prakash Dwivedi, Xavier Bresson

Comments AAAI 2021 Workshop on Deep Learning on Graphs: Methods and Applications (DLG-AAAI 2021); Code at https://github.com/graphdeeplearning/graphtransformer

Leveraging Textual Specifications for Grammar-based Fuzzing of Network Protocols

Samuel Jero, Maria Leonor Pacheco, Dan Goldwasser, Cristina Nita-Rotaru

Journal ref The Thirty-First AAAI Conference on Innovative Applications of Artificial Intelligence, IAAI 2019

The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT

Madhura Pande, Aakriti Budhraja, Preksha Nema, Pratyush Kumar, Mitesh M. Khapra

Comments accepted at AAAI 2021 (Main conference)

Automatic Volumetric Segmentation of Additive Manufacturing Defects with 3D U-Net

Vivian Wen Hui Wong, Max Ferguson, Kincho H. Law, Yung-Tsun Tina Lee, Paul Witherell

Comments Accepted by AAAI 2020 Spring Symposia

Journal ref AAAI 2020 Spring Symposia, Stanford, CA, USA, Mar 23-25, 2020

Backdoor Decomposable Monotone Circuits and their Propagation Complete Encodings

Petr Kučera, Petr Savický

Comments The paper was significantly rewritten to improve readability, it is now an extended version of the paper accepted to AAAI 2021

A Study of F0 Modification for X-Vector Based Speech Pseudonymization Across Gender

Pierre Champion, Denis Jouvet, Anthony Larcher

Journal ref The Second AAAI Workshop on Privacy-Preserving Artificial Intelligence, Feb 2021, Nancy, France

Do we need to go Deep? Knowledge Tracing with Big Data

Varun Mandalapu, Jiaqi Gong, Lujie Chen

Comments 9 Pages, 4 figures, AAAI Workshop on AI in Education (Imagining Post-COVID Education with AI)

Multi-Scale Games: Representing and Solving Games on Networks with Group Structure

Kun Jin, Yevgeniy Vorobeychik, Mingyan Liu

Comments Accepted in AAAI 2021 main conference

KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning

Ye Liu, Yao Wan, Lifang He, Hao Peng, Philip S. Yu

Comments 10 pages, 7 figures, Appear in AAAI 2021

Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data

Francesco Cartella, Orlando Anunciacao, Yuki Funabiki, Daisuke Yamaguchi, Toru Akishita, Olivier Elshocht

Comments Will be published on Proceedings of the Workshop on Artificial Intelligence Safety (SafeAI 2021) co-located with 35th AAAI Conference on Artificial Intelligence (AAAI 2021)

Learning Intuitive Physics with Multimodal Generative Models

Sahand Rezaei-Shoshtari, Francois Robert Hogan, Michael Jenkin, David Meger, Gregory Dudek

Comments AAAI 2021

Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction

Qiang Zhou, Jingjing Gu, Xinjiang Lu, Fuzhen Zhuang, Yanchao Zhao, Qiuhong Wang, Xiao Zhang

Comments Accepted by the 35th AAAI Conference on Artificial Intelligence (AAAI 2021)

HySTER: A Hybrid Spatio-Temporal Event Reasoner

Theophile Sautory, Nuri Cingillioglu, Alessandra Russo

Comments Preprint accepted by the 35th AAAI Conference on Artificial Intelligence (AAAI-21) Workshop on Hybrid Artificial Intelligence (HAI)

Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

Ardhendu Behera, Zachary Wharton, Pradeep Hewage, Asish Bera

Comments Extended version of the accepted paper in 35th AAAI Conference on Artificial Intelligence 2021

Journal ref 35th AAAI Conference on Artificial Intelligence 2021

An Empirical Comparison of Deep Learning Models for Knowledge Tracing on Large-Scale Dataset

Shalini Pandey, George Karypis, Jaideep Srivastava

Comments Accepted at AAAI workshop on AI in Education, Imagining Post-COVID Education with AI, 2021

Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requests

Jiaao Chen, Diyi Yang

Comments AAAI 2021