Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Yokohama
Edited by Christian Bessiere
Sponsored by
International Joint Conferences on Artifical Intelligence (IJCAI)
Published by
International Joint Conferences on Artificial Intelligence
Copyright © 2020 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): 978-0-9992411-6-5
Preface
Donwnload preface here.
Content
Main track
Agent-based and Multi-agent Systems
Social Ranking Manipulability for the CP-Majority, Banzhaf and Lexicographic Excellence Solutions
Speeding Up Incomplete GDL-based Algorithms for Multi-agent Optimization with Dense Local Utilities
On the Complexity of Winner Verification and Candidate Winner for Multiwinner Voting Rules
Ethics, Prosperity, and Society: Moral Evaluation Using Virtue Ethics and Utilitarianism
Logics of Allies and Enemies: A Formal Approach to the Dynamics of Social Balance Theory
Strategyproof Mechanism for Two Heterogeneous Facilities with Constant Approximation Ratio
Approximate Pareto Set for Fair and Efficient Allocation: Few Agent Types or Few Resource Types
Computational Aspects of Conditional Minisum Approval Voting in Elections with Interdependent Issues
Model-Free Real-Time Autonomous Energy Management for a Residential Multi-Carrier Energy System: A Deep Reinforcement Learning Approach
Modelling Bounded Rationality in Multi-Agent Interactions by Generalized Recursive Reasoning
AI Ethics
Computer Vision
Collaborative Learning of Depth Estimation, Visual Odometry and Camera Relocalization from Monocular Videos
Deep Interleaved Network for Single Image Super-Resolution with Asymmetric Co-Attention
Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation
SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor
Spatiotemporal Super-Resolution with Cross-Task Consistency and Its Semi-supervised Extension
Super-Resolution and Inpainting with Degraded and Upgraded Generative Adversarial Networks
GestureDet: Real-time Student Gesture Analysis with Multi-dimensional Attention-based Detector
DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue
TLPG-Tracker: Joint Learning of Target Localization and Proposal Generation for Visual Tracking
G2RL: Geometry-Guided Representation Learning for Facial Action Unit Intensity Estimation
Multi-Scale Spatial-Temporal Integration Convolutional Tube for Human Action Recognition
Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning
Position-Aware Recalibration Module: Learning From Feature Semantics and Feature Position
BARNet: Bilinear Attention Network with Adaptive Receptive Fields for Surgical Instrument Segmentation
Set and Rebase: Determining the Semantic Graph Connectivity for Unsupervised Cross-Modal Hashing
Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings
Overflow Aware Quantization: Accelerating Neural Network Inference by Low-bit Multiply-Accumulate Operations
Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error
Consistent Domain Structure Learning and Domain Alignment for 2D Image-Based 3D Objects Retrieval
Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification
Zero-Shot Object Detection via Learning an Embedding from Semantic Space to Visual Space
Hierarchical Attention Based Spatial-Temporal Graph-to-Sequence Learning for Grounded Video Description
Self-supervised Monocular Depth and Visual Odometry Learning with Scale-consistent Geometric Constraints
Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval
Co-Saliency Spatio-Temporal Interaction Network for Person Re-Identification in Videos
A Similarity Inference Metric for RGB-Infrared Cross-Modality Person Re-identification
Cross-denoising Network against Corrupted Labels in Medical Image Segmentation with Domain Shift
Overcoming Language Priors with Self-supervised Learning for Visual Question Answering
Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering
Action-Guided Attention Mining and Relation Reasoning Network for Human-Object Interaction Detection
Constraints and SAT
Diversity of Solutions: An Exploration Through the Lens of Fixed-Parameter Tractability Theory
Early and Efficient Identification of Useless Constraint Propagation for Alldifferent Constraints
Extended Conjunctive Normal Form and An Efficient Algorithm for Cardinality Constraints
Data Mining
GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
MR-GCN: Multi-Relational Graph Convolutional Networks based on Generalized Tensor Product
GraphSleepNet: Adaptive Spatial-Temporal Graph Convolutional Networks for Sleep Stage Classification
A Sequential Convolution Network for Population Flow Prediction with Explicitly Correlation Modelling
Understanding the Success of Graph-based Semi-Supervised Learning using Partially Labelled Stochastic Block Model
Online Semi-supervised Multi-label Classification with Label Compression and Local Smooth Regression
Recovering Accurate Labeling Information from Partially Valid Data for Effective Multi-Label Learning
Evidence-Aware Hierarchical Interactive Attention Networks for Explainable Claim Verification
Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization
Heuristic Search and Game Playing
Humans and AI
LISNN: Improving Spiking Neural Networks with Lateral Interactions for Robust Object Recognition
Performance as a Constraint: An Improved Wisdom of Crowds Using Performance Regularization
Aggregating Crowd Wisdom with Side Information via a Clustering-based Label-aware Autoencoder
Learning Regional Attention Convolutional Neural Network for Motion Intention Recognition Based on EEG Data
Knowledge Representation and Reasoning
Maximizing the Spread of an Opinion in Few Steps: Opinion Diffusion in Non-Binary Networks
Overcoming the Grounding Bottleneck Due to Constraints in ASP Solving: Constraints Become Propagators
Automatic Synthesis of Generalized Winning Strategies of Impartial Combinatorial Games Using SMT Solvers
Semantic Width and the Fixed-Parameter Tractability of Constraint Satisfaction Problems
Controlled Query Evaluation in Description Logics Through Instance Indistinguishability
Model-Based Synthesis of Incremental and Correct Estimators for Discrete Event Systems
Reasoning Like Human: Hierarchical Reinforcement Learning for Knowledge Graph Reasoning
Machine Learning
Stabilizing Adversarial Invariance Induction from Divergence Minimization Perspective
SI-VDNAS: Semi-Implicit Variational Dropout for Hierarchical One-shot Neural Architecture Search
Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks
Learning from Few Positives: a Provably Accurate Metric Learning Algorithm to Deal with Imbalanced Data
Location Prediction over Sparse User Mobility Traces Using RNNs: Flashback in Hidden States!
Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning
Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering
Disentangling Direct and Indirect Interactions in Polytomous Item Response Theory Models
KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge
DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction
Intention2Basket: A Neural Intention-driven Approach for Dynamic Next-basket Planning
Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer
Learning with Labeled and Unlabeled Multi-Step Transition Data for Recovering Markov Chain from Incomplete Transition Data
Convolutional Neural Networks with Compression Complexity Pooling for Out-of-Distribution Image Detection
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search
Recurrent Dirichlet Belief Networks for interpretable Dynamic Relational Data Modelling
MaCAR: Urban Traffic Light Control via Active Multi-agent Communication and Action Rectification
Balancing Individual Preferences and Shared Objectives in Multiagent Reinforcement Learning
I4R: Promoting Deep Reinforcement Learning by the Indicator for Expressive Representations
Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)
Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability
Internal and Contextual Attention Network for Cold-start Multi-channel Matching in Recommendation
Measuring the Discrepancy between Conditional Distributions: Methods, Properties and Applications
Temporal Attribute Prediction via Joint Modeling of Multi-Relational Structure Evolution
Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network
Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error
DACE: Distribution-Aware Counterfactual Explanation by Mixed-Integer Linear Optimization
Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets
Classification with Rejection: Scaling Generative Classifiers with Supervised Deep Infomax
TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure
MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics
P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection
EndCold: An End-to-End Framework for Cold Question Routing in Community Question Answering Services
pbSGD: Powered Stochastic Gradient Descent Methods for Accelerated Non-Convex Optimization
Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
Unsupervised Domain Adaptation with Dual-Scheme Fusion Network for Medical Image Segmentation
Machine Learning Applications
DeepWeave: Accelerating Job Completion Time with Deep Reinforcement Learning-based Coflow Scheduling
Generating Behavior-Diverse Game AIs with Evolutionary Multi-Objective Deep Reinforcement Learning
CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learning
Multidisciplinary Topics and Applications
Towards Alleviating Traffic Congestion: Optimal Route Planning for Massive-Scale Trips
Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising
MLS3RDUH: Deep Unsupervised Hashing via Manifold based Local Semantic Similarity Structure Reconstructing
HyperNews: Simultaneous News Recommendation and Active-Time Prediction via a Double-Task Deep Neural Network
An Attention-based Model for Conversion Rate Prediction with Delayed Feedback via Post-click Calibration
Efficient Community Search over Large Directed Graph: An Augmented Index-based Approach
An Interactive Multi-Task Learning Framework for Next POI Recommendation with Uncertain Check-ins
Natural Language Processing
How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Context
Knowledge Enhanced Event Causality Identification with Mention Masking Generalizations
EmoElicitor: An Open Domain Response Generation Model with User Emotional Reaction Awareness
Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning
Generating Reasonable Legal Text through the Combination of Language Modeling and Question Answering
A De Novo Divide-and-Merge Paradigm for Acoustic Model Optimization in Automatic Speech Recognition
Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base
TopicKA: Generating Commonsense Knowledge-Aware Dialogue Responses Towards the Recommended Topic Fact
Attention as Relation: Learning Supervised Multi-head Self-Attention for Relation Extraction
An Iterative Multi-Source Mutual Knowledge Transfer Framework for Machine Reading Comprehension
Learning with Noise: Improving Distantly-Supervised Fine-grained Entity Typing via Automatic Relabeling
On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification
CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP
Hierarchical Multi-task Learning for Organization Evaluation of Argumentative Student Essays
Alleviate Dataset Shift Problem in Fine-grained Entity Typing with Virtual Adversarial Training
Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network
UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data
Efficient Context-Aware Neural Machine Translation with Layer-Wise Weighting and Input-Aware Gating
Asking Effective and Diverse Questions: A Machine Reading Comprehension based Framework for Joint Entity-Relation Extraction
Exploring Bilingual Parallel Corpora for Syntactically Controllable Paraphrase Generation
A Structured Latent Variable Recurrent Network With Stochastic Attention For Generating Weibo Comments
ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation
Planning and Scheduling
Plan-Space Explanation via Plan-Property Dependencies: Faster Algorithms & More Powerful Properties
Sparse Tree Search Optimality Guarantees in POMDPs with Continuous Observation Spaces
Robustness Computation of Dynamic Controllability in Probabilistic Temporal Networks with Ordinary Distributions
Boundary Extension Features for Width-Based Planning with Simulators on Continuous-State Domains
Robotics
Crowd-Steer: Realtime Smooth and Collision-Free Robot Navigation in Densely Crowded Scenarios Trained using High-Fidelity Simulation
Uncertainty in AI
Learning Bayesian Networks Under Sparsity Constraints: A Parameterized Complexity Analysis
Approximate Weighted First-Order Model Counting: Exploiting Fast Approximate Model Counters and Symmetry
Special track on AI for CompSust and Human well-being
A Novel Spatio-Temporal Multi-Task Approach for the Prediction of Diabetes-Related Complication: a Cardiopathy Case of Study
Disentangled Variational Autoencoder based Multi-Label Classification with Covariance-Aware Multivariate Probit Model
Embedding Conjugate Gradient in Learning Random Walks for Landscape Connectivity Modeling in Conservation
Deep Hurdle Networks for Zero-Inflated Multi-Target Regression: Application to Multiple Species Abundance Estimation
Forecasting Avian Migration Patterns using a Deep Bidirectional RNN Augmented with an Auxiliary Task
Optimal and Non-Discriminative Rehabilitation Program Design for Opioid Addiction Among Homeless Youth
Discrete Biorthogonal Wavelet Transform Based Convolutional Neural Network for Atrial Fibrillation Diagnosis from Electrocardiogram
Real-Time Dispatching of Large-Scale Ride-Sharing Systems: Integrating Optimization, Machine Learning, and Model Predictive Control
PewLSTM: Periodic LSTM with Weather-Aware Gating Mechanism for Parking Behavior Prediction
Special Track on AI in FinTech
BitcoinHeist: Topological Data Analysis for Ransomware Prediction on the Bitcoin Blockchain
Task-Based Learning via Task-Oriented Prediction Network with Applications in Finance
F-HMTC: Detecting Financial Events for Investment Decisions Based on Neural Hierarchical Multi-Label Text Classification
Phishing Scam Detection on Ethereum: Towards Financial Security for Blockchain Ecosystem
FinBERT: A Pre-trained Financial Language Representation Model for Financial Text Mining
A Two-level Reinforcement Learning Algorithm for Ambiguous Mean-variance Portfolio Selection Problem
IGNITE: A Minimax Game Toward Learning Individual Treatment Effects from Networked Observational Data
Modeling the Stock Relation with Graph Network for Overnight Stock Movement Prediction
An End-to-End Optimal Trade Execution Framework based on Proximal Policy Optimization
WATTNet: Learning to Trade FX via Hierarchical Spatio-Temporal Representation of Highly Multivariate Time Series
``The Squawk Bot'': Joint Learning of Time Series and Text Data Modalities for Automated Financial Information Filtering
Financial Thought Experiment: A GAN-based Approach to Vast Robust Portfolio Selection
Interpretable Multimodal Learning for Intelligent Regulation in Online Payment Systems
Sister Conferences Best Papers
Hierarchical Reinforcement Learning for Pedagogical Policy Induction (Extended Abstract)
VAEP: An Objective Approach to Valuing On-the-Ball Actions in Soccer (Extended Abstract)
Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification (Extended Abstract)
A Formal Approach for Cautious Reasoning in Answer Set Programming (Extended Abstract)
Learning URI Selection Criteria to Improve the Crawling of Linked Open Data (Extended Abstract)
Bayesian Case-Exclusion and Personalized Explanations for Sustainable Dairy Farming (Extended Abstract)
Specializing Word Embeddings (for Parsing) by Information Bottleneck (Extended Abstract)
NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm (Extended Abstract)
Supporting Historical Photo Identification with Face Recognition and Crowdsourced Human Expertise (Extended Abstract)
Commonsense Reasoning to Guide Deep Learning for Scene Understanding (Extended Abstract)
Deep Visuo-Tactile Learning: Estimation of Tactile Properties from Images (Extended Abstract)
Survey track
The Blind Men and the Elephant: Integrated Offline/Online Optimization Under Uncertainty
From Standard Summarization to New Tasks and Beyond: Summarization with Manifold Information
A Brief History of Learning Symbolic Higher-Level Representations from Data (And a Curious Look Forward)
Collective Decision Making under Incomplete Knowledge: Possible and Necessary Solutions
Planning Algorithms for Zero-Sum Games with Exponential Action Spaces: A Unifying Perspective
The Knowledge Acquisition Bottleneck Problem in Multilingual Word Sense Disambiguation
Journal track
Xeggora: Exploiting Immune-to-Evidence Symmetries with Full Aggregation in Statistical Relational Models (Extended Abstract)
Automated Construction of Bounded-Loss Imperfect-Recall Abstractions in Extensive-Form Games (Extended Abstract)
Algorithms for Estimating the Partition Function of Restricted Boltzmann Machines (Extended Abstract)
On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)
Story Embedding: Learning Distributed Representations of Stories based on Character Networks (Extended Abstract)
Point at the Triple: Generation of Text Summaries from Knowledge Base Triples (Extended Abstract)
A Survey on Temporal Reasoning for Temporal Information Extraction from Text (Extended Abstract)
Formulas Free From Inconsistency: An Atom-Centric Characterization in Priest's Minimally Inconsistent LP (Extended Abstract)
Catching Cheats: Detecting Strategic Manipulation in Distributed Optimisation of Electric Vehicle Aggregators (Extended Abstract)
From Support Propagation to Belief Propagation in Constraint Programming (Extended Abstract)
Language Independent Sequence Labelling for Opinion Target Extraction (Extended Abstract)
Context Vectors Are Reflections of Word Vectors in Half the Dimensions (Extended Abstract)
Best-first Enumeration Based on Bounding Conflicts, and its Application to Large-scale Hybrid Estimation (Extended Abstract)
Incentivizing Evaluation with Peer Prediction and Limited Access to Ground Truth (Extended Abstract)
Early Career
Closing the Loop: Bringing Humans into Empirical Computational Social Choice and Preference Reasoning
Doctoral Consortium
Social Network Analysis using RLVECN: Representation Learning via Knowledge-Graph Embeddings and Convolutional Neural-Network
Beyond Labels: Knowledge Elicitation using Deep Metric Learning and Psychometric Testing
Demos
An Anomaly Detection and Explainability Framework using Convolutional Autoencoders for Data Storage Systems
How Causal Structural Knowledge Adds Decision-Support in Monitoring of Automotive Body Shop Assembly Lines
FlowSynth: Simplifying Complex Audio Generation Through Explorable Latent Spaces with Normalizing Flows
Inspection of Blackbox Models for Evaluating Vulnerability in Maternal, Newborn, and Child Health
Decision Platform for Pattern Discovery and Causal Effect Estimation in Contraceptive Discontinuation
A Gamified Assessment Platform for Predicting the Risk of Dementia +Parkinson’s disease (DPD) Co-Morbidity
SiamBOMB: A Real-time AI-based System for Home-cage Animal Tracking, Segmentation and Behavioral Analysis
Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization