Proceedings of the Twenty-Eigth International Joint Conference on Artificial Intelligence
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Macao, 10-16 August 2019
Edited by Sarit Kraus
Sponsored by
International Joint Conferences on Artifical Intelligence (IJCAI)
Published by
International Joint Conferences on Artificial Intelligence
Sponsored by
International Joint Conferences on Artifical Intelligence (IJCAI)
Published by
International Joint Conferences on Artificial Intelligence
Copyright © 2019 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): 978-0-9992411-4-1
Preface
Donwnload preface here.
Content
Main track
Agent-based and Multi-agent Systems
An Efficient Algorithm for Skeptical Preferred Acceptance in Dynamic Argumentation Frameworks
Optimality and Nash Stability in Additive Separable Generalized Group Activity Selection Problems
Civic Crowdfunding for Agents with Negative Valuations and Agents with Asymmetric Beliefs
AsymDPOP: Complete Inference for Asymmetric Distributed Constraint Optimization Problems
An Asymptotically Optimal VCG Redistribution Mechanism for the Public Project Problem
Swarm Engineering Through Quantitative Measurement of Swarm Robotic Principles in a 10,000 Robot Swarm
Integrating Decision Sharing with Prediction in Decentralized Planning for Multi-Agent Coordination under Uncertainty
Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns
Computing Approximate Equilibria in Sequential Adversarial Games by Exploitability Descent
FaRM: Fair Reward Mechanism for Information Aggregation in Spontaneous Localized Settings
Large-Scale Home Energy Management Using Entropy-Based Collective Multiagent Deep Reinforcement Learning Framework
The Price of Governance: A Middle Ground Solution to Coordination in Organizational Control
Computer Vision
Generalized Zero-Shot Vehicle Detection in Remote Sensing Imagery via Coarse-to-Fine Framework
Connectionist Temporal Modeling of Video and Language: a Joint Model for Translation and Sign Labeling
3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention
Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views
Multi-Level Visual-Semantic Alignments with Relation-Wise Dual Attention Network for Image and Text Matching
Pedestrian Attribute Recognition by Joint Visual-semantic Reasoning and Knowledge Distillation
Capturing Spatial and Temporal Patterns for Facial Landmark Tracking through Adversarial Learning
Binarized Neural Networks for Resource-Efficient Hashing with Minimizing Quantization Loss
LRDNN: Local-refining based Deep Neural Network for Person Re-Identification with Attribute Discerning
Constraints and SAT
Constraint-Based Scheduling with Complex Setup Operations: An Iterative Two-Layer Approach
Unifying Search-based and Compilation-based Approaches to Multi-agent Path Finding through Satisfiability Modulo Theories
Integrating Pseudo-Boolean Constraint Reasoning in Multi-Objective Evolutionary Algorithms
Heuristic Search and Game Playing
Learning Deep Decentralized Policy Network by Collective Rewards for Real-Time Combat Game
Heuristic Search for Homology Localization Problem and Its Application in Cardiac Trabeculae Reconstruction
Humans and AI
STCA: Spatio-Temporal Credit Assignment with Delayed Feedback in Deep Spiking Neural Networks
DeepFlow: Detecting Optimal User Experience From Physiological Data Using Deep Neural Networks
Fast and Accurate Classification with a Multi-Spike Learning Algorithm for Spiking Neurons
DeepAPF: Deep Attentive Probabilistic Factorization for Multi-site Video Recommendation
Knowledge Representation and Reasoning
Worst-Case Optimal Querying of Very Expressive Description Logics with Path Expressions and Succinct Counting
Planning for LTLf /LDLf Goals in Non-Markovian Fully Observable Nondeterministic Domains
From Statistical Transportability to Estimating the Effect of Stochastic Interventions
An ASP Approach to Generate Minimal Countermodels in Intuitionistic Propositional Logic
Learning Description Logic Concepts: When can Positive and Negative Examples be Separated?
Aggressive Driving Saves More Time? Multi-task Learning for Customized Travel Time Estimation
Approximating Integer Solution Counting via Space Quantification for Linear Constraints
On Finite and Unrestricted Query Entailment beyond SQ with Number Restrictions on Transitive Roles
Travel Time Estimation without Road Networks: An Urban Morphological Layout Representation Approach
Geo-ALM: POI Recommendation by Fusing Geographical Information and Adversarial Learning Mechanism
Automatic Verification of FSA Strategies via Counterexample-Guided Local Search for Invariants
BiOWA for Preference Aggregation with Bipolar Scales: Application to Fair Optimization in Combinatorial Domains
Data Complexity and Rewritability of Ontology-Mediated Queries in Metric Temporal Logic under the Event-Based Semantics
Out of Sight But Not Out of Mind: An Answer Set Programming Based Online Abduction Framework for Visual Sensemaking in Autonomous Driving
TransMS: Knowledge Graph Embedding for Complex Relations by Multidirectional Semantics
Machine Learning A-L
Human-in-the-loop Active Covariance Learning for Improving Prediction in Small Data Sets
Unobserved Is Not Equal to Non-existent: Using Gaussian Processes to Infer Immediate Rewards Across Contexts
STG2Seq: Spatial-Temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting
An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments
Incremental Elicitation of Rank-Dependent Aggregation Functions based on Bayesian Linear Regression
Active Learning within Constrained Environments through Imitation of an Expert Questioner
Tree Sampling Divergence: An Information-Theoretic Metric for Hierarchical Graph Clustering
FakeTables: Using GANs to Generate Functional Dependency Preserving Tables with Bounded Real Data
Matching User with Item Set: Collaborative Bundle Recommendation with Deep Attention Network
Learn Smart with Less: Building Better Online Decision Trees with Fewer Training Examples
iDev: Enhancing Social Coding Security by Cross-platform User Identification Between GitHub and Stack Overflow
Advocacy Learning: Learning through Competition and Class-Conditional Representations
Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing
Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces
Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation
Perception-Aware Point-Based Value Iteration for Partially Observable Markov Decision Processes
Efficient Regularization Parameter Selection for Latent Variable Graphical Models via Bi-Level Optimization
Confirmatory Bayesian Online Change Point Detection in the Covariance Structure of Gaussian Processes
One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Networks
Group-based Learning of Disentangled Representations with Generalizability for Novel Contents
Cascaded Algorithm-Selection and Hyper-Parameter Optimization with Extreme-Region Upper Confidence Bound Bandit
Zeroth-Order Stochastic Alternating Direction Method of Multipliers for Nonconvex Nonsmooth Optimization
Nostalgic Adam: Weighting More of the Past Gradients When Designing the Adaptive Learning Rate
SlateQ: A Tractable Decomposition for Reinforcement Learning with Recommendation Sets
Recurrent Generative Networks for Multi-Resolution Satellite Data: An Application in Cropland Monitoring
Twin-Systems to Explain Artificial Neural Networks using Case-Based Reasoning: Comparative Tests of Feature-Weighting Methods in ANN-CBR Twins for XAI
What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features
Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks
Cascading Non-Stationary Bandits: Online Learning to Rank in the Non-Stationary Cascade Model
Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting
Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Loss
GCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks
Learning K-way D-dimensional Discrete Embedding for Hierarchical Data Visualization and Retrieval
Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustness
Learning Robust Distance Metric with Side Information via Ratio Minimization of Orthogonally Constrained L21-Norm Distances
Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph
Accelerated Incremental Gradient Descent using Momentum Acceleration with Scaling Factor
E²GAN: End-to-End Generative Adversarial Network for Multivariate Time Series Imputation
Machine Learning M-Z
Coarse-to-Fine Image Inpainting via Region-wise Convolutions and Non-Local Correlation
Unsupervised Hierarchical Temporal Abstraction by Simultaneously Learning Expectations and Representations
Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems
Deep Variational Koopman Models: Inferring Koopman Observations for Uncertainty-Aware Dynamics Modeling and Control
DyAt Nets: Dynamic Attention Networks for State Forecasting in Cyber-Physical Systems
An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
Improving representation learning in autoencoders via multidimensional interpolation and dual regularizations
Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay
Discovering Regularities from Traditional Chinese Medicine Prescriptions via Bipartite Embedding Model
Deterministic Routing between Layout Abstractions for Multi-Scale Classification of Visually Rich Documents
Community Detection and Link Prediction via Cluster-driven Low-rank Matrix Completion
A Convergence Analysis of Distributed SGD with Communication-Efficient Gradient Sparsification
Quadruply Stochastic Gradients for Large Scale Nonlinear Semi-Supervised AUC Optimization
The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning
Multiplicative Sparse Feature Decomposition for Efficient Multi-View Multi-Task Learning
Hierarchical Inter-Attention Network for Document Classification with Multi-Task Learning
Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning
DeepCU: Integrating both Common and Unique Latent Information for Multimodal Sentiment Analysis
CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets
Modeling Multi-Purpose Sessions for Next-Item Recommendations via Mixture-Channel Purpose Routing Networks
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
Unified Embedding Model over Heterogeneous Information Network for Personalized Recommendation
Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human and Agent Demonstrations
Learning Multi-Objective Rewards and User Utility Function in Contextual Bandits for Personalized Ranking
RobustTrend: A Huber Loss with a Combined First and Second Order Difference Regularization for Time Series Trend Filtering
Feature Evolution Based Multi-Task Learning for Collaborative Filtering with Social Trust
Graph Convolutional Networks on User Mobility Heterogeneous Graphs for Social Relationship Inference
Learning a Generative Model for Fusing Infrared and Visible Images via Conditional Generative Adversarial Network with Dual Discriminators
MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
On the Convergence of (Stochastic) Gradient Descent with Extrapolation for Non-Convex Minimization
Deep Correlated Predictive Subspace Learning for Incomplete Multi-View Semi-Supervised Classification
Learning Strictly Orthogonal p-Order Nonnegative Laplacian Embedding via Smoothed Iterative Reweighted Method
Dual Self-Paced Graph Convolutional Network: Towards Reducing Attribute Distortions Induced by Topology
Privacy-Preserving Stacking with Application to Cross-organizational Diabetes Prediction
Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers
A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment
Out-of-sample Node Representation Learning for Heterogeneous Graph in Real-time Android Malware Detection
Neural Network based Continuous Conditional Random Field for Fine-grained Crime Prediction
Metatrace Actor-Critic: Online Step-Size Tuning by Meta-gradient Descent for Reinforcement Learning Control
VAEGAN: A Collaborative Filtering Framework based on Adversarial Variational Autoencoders
Adaptive User Modeling with Long and Short-Term Preferences for Personalized Recommendation
DARec: Deep Domain Adaptation for Cross-Domain Recommendation via Transferring Rating Patterns
KCNN: Kernel-wise Quantization to Remarkably Decrease Multiplications in Convolutional Neural Network
STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
Multi-Group Encoder-Decoder Networks to Fuse Heterogeneous Data for Next-Day Air Quality Prediction
Accelerated Inference Framework of Sparse Neural Network Based on Nested Bitmask Structure
Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks
Collaborative Metric Learning with Memory Network for Multi-Relational Recommender Systems
Machine Learning Applications
A Quantum-inspired Classical Algorithm for Separable Non-negative Matrix Factorization
MLRDA: A Multi-Task Semi-Supervised Learning Framework for Drug-Drug Interaction Prediction
Combining ADMM and the Augmented Lagrangian Method for Efficiently Handling Many Constraints
FSM: A Fast Similarity Measurement for Gene Regulatory Networks via Genes' Influence Power
Dynamic Electronic Toll Collection via Multi-Agent Deep Reinforcement Learning with Edge-Based Graph Convolutional Networks
Faster Distributed Deep Net Training: Computation and Communication Decoupled Stochastic Gradient Descent
Learning Shared Vertex Representation in Heterogeneous Graphs with Convolutional Networks for Recommendation
Multidisciplinary Topics and Applications
DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks
Locate-Then-Detect: Real-time Web Attack Detection via Attention-based Deep Neural Networks
LogAnomaly: Unsupervised Detection of Sequential and Quantitative Anomalies in Unstructured Logs
Decidability of Model Checking Multi-Agent Systems with Regular Expressions against Epistemic HS Specifications
Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness
Demystifying the Combination of Dynamic Slicing and Spectrum-based Fault Localization
Two-Stage Generative Models of Simulating Training Data at The Voxel Level for Large-Scale Microscopy Bioimage Segmentation
FABA: An Algorithm for Fast Aggregation against Byzantine Attacks in Distributed Neural Networks
BAYHENN: Combining Bayesian Deep Learning and Homomorphic Encryption for Secure DNN Inference
Natural Language Processing
Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection
From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots
Answering Binary Causal Questions Through Large-Scale Text Mining: An Evaluation Using Cause-Effect Pairs from Human Experts
Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities
Deep Mask Memory Network with Semantic Dependency and Context Moment for Aspect Level Sentiment Classification
Improving Cross-Domain Performance for Relation Extraction via Dependency Prediction and Information Flow Control
Cold-Start Aware Deep Memory Network for Multi-Entity Aspect-Based Sentiment Analysis
Revealing Semantic Structures of Texts: Multi-grained Framework for Automatic Mind-map Generation
Modeling Noisy Hierarchical Types in Fine-Grained Entity Typing: A Content-Based Weighting Approach
Polygon-Net: A General Framework for Jointly Boosting Multiple Unsupervised Neural Machine Translation Models
HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning
Knowledge-enhanced Hierarchical Attention for Community Question Answering with Multi-task and Adaptive Learning
Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling
Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmax
Modeling both Context- and Speaker-Sensitive Dependence for Emotion Detection in Multi-speaker Conversations
Extracting Entities and Events as a Single Task Using a Transition-Based Neural Model
A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots
Recurrent Neural Network for Text Classification with Hierarchical Multiscale Dense Connections
Dynamically Route Hierarchical Structure Representation to Attentive Capsule for Text Classification
Planning and Scheduling
Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks
Fair Online Allocation of Perishable Goods and its Application to Electric Vehicle Charging
Bayesian Inference of Linear Temporal Logic Specifications for Contrastive Explanations
On Computational Complexity of Pickup-and-Delivery Problems with Precedence Constraints or Time Windows
Robotics
Energy-Efficient Slithering Gait Exploration for a Snake-Like Robot Based on Reinforcement Learning
Uncertainty in AI
An End-to-End Community Detection Model: Integrating LDA into Markov Random Field via Factor Graph
Cutset Bayesian Networks: A New Representation for Learning Rao-Blackwellised Graphical Models
ISLF: Interest Shift and Latent Factors Combination Model for Session-based Recommendation
AI for Improving Human Well-being
SparseSense: Human Activity Recognition from Highly Sparse Sensor Data-streams Using Set-based Neural Networks
Evaluating the Interpretability of the Knowledge Compilation Map: Communicating Logical Statements Effectively
AI-powered Posture Training: Application of Machine Learning in Sitting Posture Recognition Using the LifeChair Smart Cushion
Improving Law Enforcement Daily Deployment Through Machine Learning-Informed Optimization under Uncertainty
Risk Assessment for Networked-guarantee Loans Using High-order Graph Attention Representation
Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuning
Improving Customer Satisfaction in Bike Sharing Systems through Dynamic Repositioning
Systematic Conservation Planning for Sustainable Land-use Policies: A Constrained Partitioning Approach to Reserve Selection and Design.
Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies
KitcheNette: Predicting and Ranking Food Ingredient Pairings using Siamese Neural Network
Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the Hamming Distance
Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving
Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses
Who Should Pay the Cost: A Game-theoretic Model for Government Subsidized Investments to Improve National Cybersecurity
Understanding Intelligence and Human-level AI in the New Machine Learning era
LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning
Learning Hierarchical Symbolic Representations to Support Interactive Task Learning and Knowledge Transfer
How Well Do Machines Perform on IQ tests: a Comparison Study on a Large-Scale Dataset
Best Sister Conferences
Closed-World Semantics for Conjunctive Queries with Negation over ELH-bottom Ontologies
Impact of Consuming Suggested Items on the Assessment of Recommendations in User Studies on Recommender Systems
Trust Dynamics and Transfer across Human-Robot Interaction Tasks: Bayesian and Neural Computational Models
Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning - Extended Abtract
Survey track
Counterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning
Journal track
Learning in the Machine: Random Backpropagation and the Deep Learning Channel (Extended Abstract)
Complexity Bounds for the Controllability of Temporal Networks with Conditions, Disjunctions, and Uncertainty (Extended Abstract)
A Core Method for the Weak Completion Semantics with Skeptical Abduction (Extended Abstract)
Complexity of Fundamental Problems in Probabilistic Abstract Argumentation: Beyond Independence (Extended Abstract)
Implicitly Coordinated Multi-Agent Path Finding under Destination Uncertainty: Success Guarantees and Computational Complexity (Extended Abstract)
Teaching AI Agents Ethical Values Using Reinforcement Learning and Policy Orchestration
Early Career
Doctoral Consortium
A Unified Mathematical Approach for Foraging and Construction Systems in a 1,000,000 Robot Swarm
Can Meta-Interpretive Learning outperform Deep Reinforcement Learning of Evaluable Game strategies?
Event Prediction in Complex Social Graphs using One-Dimensional Convolutional Neural Network
Safe and Sample-Efficient Reinforcement Learning Algorithms for Factored Environments
Demos
AntProphet: an Intention Mining System behind Alipay's Intelligent Customer Service Bot
Demonstration of PerformanceNet: A Convolutional Neural Network Model for Score-to-Audio Music Generation
The Open Vault Challenge - Learning How to Build Calibration-Free Interactive Systems by Cracking the Code of a Vault
The pywmi Framework and Toolbox for Probabilistic Inference using Weighted Model Integration
Design and Implementation of a Disambiguity Framework for Smart Voice Controlled Devices
A Quantitative Analysis Platform for PD-L1 Immunohistochemistry based on Point-level Supervision Model