Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Montreal, 19-27 August 2021
Edited by Prof. Zhi-Hua Zhou
Sponsored by
International Joint Conferences on Artifical Intelligence (IJCAI)
Published by
International Joint Conferences on Artificial Intelligence
Copyright © 2021 International Joint Conferences on Artificial Intelligence
All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means (including photocopying, recording, or information storage and retrieval) without permission in writing from the publisher.
IJCAI Secretary-Treasurer: Prof. Dr. Bernhard Nebel, Computer Science Department, Albert-Ludwigs-Universitaet Freiburg, Georges-Koehler-Allee, Geb. 052 D-79110 Freiburg, Germany
IJCAI Executive Secretary Ms. Vesna Sabljakovic-Fritz, Vienna University of Technology, Institute of Discrete Mathematics and Geometry, E104 Wiedner Hauptstr. 8-10, A-1040 Vienna, Austria
ISBN (Online): 978-0-9992411-9-6
Content
Main Track
Agent-based and Multi-agent Systems
Winner Robustness via Swap- and Shift-Bribery: Parameterized Counting Complexity and Experiments
Worst-case Bounds on Power vs. Proportion in Weighted Voting Games with Application to False-name Manipulation
Even More Effort Towards Improved Bounds and Fixed-Parameter Tractability for Multiwinner Rules
A Polynomial-time, Truthful, Individually Rational and Budget Balanced Ridesharing Mechanism
Majority Vote in Social Networks: Make Random Friends or Be Stubborn to Overpower Elites
State-Aware Value Function Approximation with Attention Mechanism for Restless Multi-armed Bandits
H-FL: A Hierarchical Communication-Efficient and Privacy-Protected Architecture for Federated Learning
AI Ethics, Trust, Fairness
Location Predicts You: Location Prediction via Bi-direction Speculation and Dual-level Association
Bias Silhouette Analysis: Towards Assessing the Quality of Bias Metrics for Word Embedding Models
Computer Vision I
Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning
IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement
A Multi-Constraint Similarity Learning with Adaptive Weighting for Visible-Thermal Person Re-Identification
Graph Consistency Based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification
Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference
Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks
Computer Vision II
Speech2Talking-Face: Inferring and Driving a Face with Synchronized Audio-Visual Representation
MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction
Tag, Copy or Predict: A Unified Weakly-Supervised Learning Framework for Visual Information Extraction using Sequences
Local Representation is Not Enough: Soft Point-Wise Transformer for Descriptor and Detector of Local Features
Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching
Micro-Expression Recognition Enhanced by Macro-Expression from Spatial-Temporal Domain
Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metrics
Non-contact Pain Recognition from Video Sequences with Remote Physiological Measurements Prediction
Object Detection in Densely Packed Scenes via Semi-Supervised Learning with Dual Consistency
Low Resolution Information Also Matters: Learning Multi-Resolution Representations for Person Re-Identification
Constraints and SAT
Solving Graph Homomorphism and Subgraph Isomorphism Problems Faster Through Clique Neighbourhood Constraints
Data Mining
Exploring Periodicity and Interactivity in Multi-Interest Framework for Sequential Recommendation
Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning
Discovering Collaborative Signals for Next POI Recommendation with Iterative Seq2Graph Augmentation
MG-DVD: A Real-time Framework for Malware Variant Detection Based on Dynamic Heterogeneous Graph Learning
Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy
Does Every Data Instance Matter? Enhancing Sequential Recommendation by Eliminating Unreliable Data
Cooperative Joint Attentive Network for Patient Outcome Prediction on Irregular Multi-Rate Multivariate Health Data
User-as-Graph: User Modeling with Heterogeneous Graph Pooling for News Recommendation
Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learning
Heuristic Search and Game Playing
Faster Guarantees of Evolutionary Algorithms for Maximization of Monotone Submodular Functions
A Runtime Analysis of Typical Decomposition Approaches in MOEA/D Framework for Many-objective Optimization Problems
Humans and AI
Knowledge Representation and Reasoning
On Cycles, Attackers and Supporters --- A Contribution to The Investigation of Dynamics in Abstract Argumentation
How Hard to Tell? Complexity of Belief Manipulation Through Propositional Announcements
Using Platform Models for a Guided Explanatory Diagnosis Generation for Mobile Robots
HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
Signature-Based Abduction with Fresh Individuals and Complex Concepts for Description Logics
Inferring Time-delayed Causal Relations in POMDPs from the Principle of Independence of Cause and Mechanism
Reasoning about Beliefs and Meta-Beliefs by Regression in an Expressive Probabilistic Action Logic
Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding
Skeptical Reasoning with Preferred Semantics in Abstract Argumentation without Computing Preferred Extensions
Transforming Robotic Plans with Timed Automata to Solve Temporal Platform Constraints
Neighborhood Intervention Consistency: Measuring Confidence for Knowledge Graph Link Prediction
Machine Learning
Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)
DEHB: Evolutionary Hyberband for Scalable, Robust and Efficient Hyperparameter Optimization
Efficient Neural Network Verification via Layer-based Semidefinite Relaxations and Linear Cuts
Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment
AMA-GCN: Adaptive Multi-layer Aggregation Graph Convolutional Network for Disease Prediction
Learning Attributed Graph Representation with Communicative Message Passing Transformer
Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks
BAMBOO: A Multi-instance Multi-label Approach Towards VDI User Logon Behavior Modeling
Learning Nash Equilibria in Zero-Sum Stochastic Games via Entropy-Regularized Policy Approximation
DA-GCN: A Domain-aware Attentive Graph Convolution Network for Shared-account Cross-domain Sequential Recommendation
Enabling Retrain-free Deep Neural Network Pruning Using Surrogate Lagrangian Relaxation
Model-Based Reinforcement Learning for Infinite-Horizon Discounted Constrained Markov Decision Processes
State-Based Recurrent SPMNs for Decision-Theoretic Planning under Partial Observability
DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis
Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning
Learning to Learn Personalized Neural Network for Ventricular Arrhythmias Detection on Intracardiac EGMs
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation
Towards Scalable Complete Verification of Relu Neural Networks via Dependency-based Branching
Topological Uncertainty: Monitoring Trained Neural Networks through Persistence of Activation Graphs
TextGTL: Graph-based Transductive Learning for Semi-supervised Text Classification via Structure-Sensitive Interpolation
Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks
An Adaptive News-Driven Method for CVaR-sensitive Online Portfolio Selection in Non-Stationary Financial Markets
Residential Electric Load Forecasting via Attentive Transfer of Graph Neural Networks
Smart Contract Vulnerability Detection: From Pure Neural Network to Interpretable Graph Feature and Expert Pattern Fusion
Transfer Learning via Optimal Transportation for Integrative Cancer Patient Stratification
Hierarchical Temporal Multi-Instance Learning for Video-based Student Learning Engagement Assessment
TIDOT: A Teacher Imitation Learning Approach for Domain Adaptation with Optimal Transport
Two Birds with One Stone: Series Saliency for Accurate and Interpretable Multivariate Time Series Forecasting
Multi-Agent Reinforcement Learning for Automated Peer-to-Peer Energy Trading in Double-Side Auction Market
TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data
Hyperspectral Band Selection via Spatial-Spectral Weighted Region-wise Multiple Graph Fusion-Based Spectral Clustering
Sensitivity Direction Learning with Neural Networks Using Domain Knowledge as Soft Shape Constraints
Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity
Self-Supervised Adversarial Distribution Regularization for Medication Recommendation
Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models
Closing the BIG-LID: An Effective Local Intrinsic Dimensionality Defense for Nonlinear Regression Poisoning
GSPL: A Succinct Kernel Model for Group-Sparse Projections Learning of Multiview Data
Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning
k-Nearest Neighbors by Means of Sequence to Sequence Deep Neural Networks and Memory Networks
Clustering-Induced Adaptive Structure Enhancing Network for Incomplete Multi-View Data
Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels with Variational Auto-Encoder
Rethink the Connections among Generalization, Memorization, and the Spectral Bias of DNNs
Neural Relation Inference for Multi-dimensional Temporal Point Processes via Message Passing Graph
Combining Tree Search and Action Prediction for State-of-the-Art Performance in DouDiZhu
Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning
Machine Learning Applications
Sample Efficient Decentralized Stochastic Frank-Wolfe Methods for Continuous DR-Submodular Maximization
Collaborative Graph Learning with Auxiliary Text for Temporal Event Prediction in Healthcare
TEC: A Time Evolving Contextual Graph Model for Speaker State Analysis in Political Debates
Adaptive Residue-wise Profile Fusion for Low Homologous Protein Secondary Structure Prediction Using External Knowledge
Multidisciplinary Topics and Applications
TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning
Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models
Dynamic Lane Traffic Signal Control with Group Attention and Multi-Timescale Reinforcement Learning
Traffic Congestion Alleviation over Dynamic Road Networks: Continuous Optimal Route Combination for Trip Query Streams
CFR-MIX: Solving Imperfect Information Extensive-Form Games with Combinatorial Action Space
Online Credit Payment Fraud Detection via Structure-Aware Hierarchical Recurrent Neural Network
Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction
Adapting Meta Knowledge with Heterogeneous Information Network for COVID-19 Themed Malicious Repository Detection
Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play
SafeDrug: Dual Molecular Graph Encoders for Recommending Effective and Safe Drug Combinations
CSGNN: Contrastive Self-Supervised Graph Neural Network for Molecular Interaction Prediction
Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling
Natural Language Processing
Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling
Improving Context-Aware Neural Machine Translation with Source-side Monolingual Documents
Focus on Interaction: A Novel Dynamic Graph Model for Joint Multiple Intent Detection and Slot Filling
Enhancing Label Representations with Relational Inductive Bias Constraint for Fine-Grained Entity Typing
Modelling General Properties of Nouns by Selectively Averaging Contextualised Embeddings
Asynchronous Multi-grained Graph Network For Interpretable Multi-hop Reading Comprehension
MultiMirror: Neural Cross-lingual Word Alignment for Multilingual Word Sense Disambiguation
Hierarchical Modeling of Label Dependency and Label Noise in Fine-grained Entity Typing
Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge
Knowledge-Aware Dialogue Generation via Hierarchical Infobox Accessing and Infobox-Dialogue Interaction Graph Network
UniMF: A Unified Framework to Incorporate Multimodal Knowledge Bases intoEnd-to-End Task-Oriented Dialogue Systems
Drop Redundant, Shrink Irrelevant: Selective Knowledge Injection for Language Pretraining
Planning and Scheduling
Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare
Symbolic Dynamic Programming for Continuous State MDPs with Linear Program Transitions
Counterfactual Explanations for Optimization-Based Decisions in the Context of the GDPR
Polynomial-Time in PDDL Input Size: Making the Delete Relaxation Feasible for Lifted Planning
Dynamic Rebalancing Dockless Bike-Sharing System based on Station Community Discovery
Change the World - How Hard Can that Be? On the Computational Complexity of Fixing Planning Models
TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators
Uncertainty in AI
BKT-POMDP: Fast Action Selection for User Skill Modelling over Tasks with Multiple Skills
Improved Acyclicity Reasoning for Bayesian Network Structure Learning with Constraint Programming
Survey Track
When Computational Representation Meets Neuroscience: A Survey on Brain Encoding and Decoding
Understanding the Relationship between Interactions and Outcomes in Human-in-the-Loop Machine Learning
Optimal Transport for Deep Generative Models: State of the Art and Research Challenges
If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques
A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions
What’s the Context? Implicit and Explicit Assumptions in Model-Based Goal Recognition
A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI Interaction
Information-Theoretic Methods in Deep Neural Networks: Recent Advances and Emerging Opportunities
Sister Conferences Best Papers
Hierarchical Graph Traversal for Aggregate k Nearest Neighbors Search in Road Networks (Extended Abstract)
Defining the Semantics of Abstract Argumentation Frameworks through Logic Programs and Partial Stable Models (Extended Abstract)
Comparing Weak Admissibility Semantics to their Dung-style Counterparts (Extended Abstract)
Robust Domain Adaptation: Representations, Weights and Inductive Bias (Extended Abstract)
Decentralized No-regret Learning Algorithms for Extensive-form Correlated Equilibria (Extended Abstract)
Weaving a Semantic Web of Credibility Reviews for Explainable Misinformation Detection (Extended Abstract)
Improved Guarantees and a Multiple-descent Curve for Column Subset Selection and the Nystrom Method (Extended Abstract)
Successor-Invariant First-Order Logic on Classes of Bounded Degree (Extended Abstract)
Revisiting Wedge Sampling for Budgeted Maximum Inner Product Search (Extended Abstract)
The Moodoo Library: Quantitative Metrics to Model How Teachers Make Use of the Classroom Space by Analysing Indoor Positioning Traces (Extended Abstract)
Unifying Online and Counterfactual Learning to Rank: A Novel Counterfactual Estimator that Effectively Utilizes Online Interventions (Extended Abstract)
Exploring the Effects of Goal Setting When Training for Complex Crowdsourcing Tasks (Extended Abstract)
Imprecise Oracles Impose Limits to Predictability in Supervised Learning (Extended Abstract)
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild (Extended Abstract)
TAXOGAN: Hierarchical Network Representation Learning via Taxonomy Guided Generative Adversarial Networks (Extended Abstract)
Doctoral Consortium
Bottleneck Identification to Semantic Segmentation of Industrial 3D Point Cloud Scene via Deep Learning
An Information-Theoretic Approach on Causal Structure Learning for Heterogeneous Data Characteristics of Real-World Scenarios
Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems
An Automated Framework for Supporting Data-Governance Rule Compliance in Decentralized MIMO Contexts
Early Career
Width-Based Algorithms for Common Problems in Control, Planning and Reinforcement Learning
Demo Track
InfOCF-Web: An Online Tool for Nonmonotonic Reasoning with Conditionals and Ranking Functions
Interactive Video Acquisition and Learning System for Motor Assessment of Parkinson's Disease
IIAS: An Intelligent Insurance Assessment System through Online Real-time Conversation Analysis