Australasian Conference on Artificial Intelligence 2019

24 papers
The 2019 Australasian Conference on Artificial Intelligence featured 35 papers covering a broad spectrum of machine learning and optimization topics. A significant portion of the research focused on improving learning efficiency and addressing data limitations, with themes such as few-shot learning, semi-supervised learning through iterative pseudo-labeling, and methods for overcoming labeling bottlenecks in deep learning. Theoretical explorations were also prominent, including studies on learning bounds in uncountable hypothesis spaces and the limitations of instance optimality in offline learning. Notable authors contributing to this edition included Santu Rana, Svetha Venkatesh, and Peter Vamplew. Applied research spanned diverse domains, from air combat maneuvering simulations using actor-critic reinforcement learning to financial well-being prediction via gradient boosting. The conference also highlighted advancements in structural and representation learning, such as motif-based graph networks and the analysis of contextualized word representations. Other technical contributions addressed security through Bayesian optimization for detecting compromised models and industrial optimization using genetic programming for job shop scheduling. These works reflect a balanced focus between foundational machine learning theory and practical algorithmic applications in complex environments.

Top Research Directions

The 3 research directions with Australasian Conference on Artificial Intelligence 2019 papers, ranked by paper count, next to 2018. Share is the fraction of the edition’s papers in the direction.

#Direction20192018Share 2019Share 20182018 rank
1Informed Initialization for Bayesian Optimization104.2%0.0%—
2Prototype Based Classification in Embedding Spaces104.2%0.0%—
3Robustness to Prior Misspecification in Sequential Optimization104.2%0.0%—

Download all directions as CSV

Institutions

Institutions credited by Australasian Conference on Artificial Intelligence 2019 papers: a paper credits every institution named in its affiliations, once. 5 institutions share 3 credited papers.

#InstitutionPapersShare20182018 rank
1Dalian University of Technology 133.3%0—
2Federation University 133.3%0—
3Harvey Mudd College 133.3%0—
4University of South Australia 133.3%0—
5University of Waikato 133.3%0—

Download all institutions as CSV

About this data

Papers. Australasian Conference on Artificial Intelligence 2019 lists 24 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers. Comparisons with 2018 use shares, since the edition went from 31 to 24 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 3 of 24 papers (12.5%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-22 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Australasian Conference on Artificial Intelligence 2019”, https://lacuna.tiptreesystems.com/venue/australasian-conference-on-artificial-intelligence/2019.

Top Authors

AuthorPapers
Santu Rana4
Sunil Gupta4
Svetha Venkatesh4
Bing Xue2
Dang Nguyen2
Feng Xia2
Gang Chen2
Mengjie Zhang2
Peter Vamplew2
Alistair Shilton1
Bernhard Pfahringer1
Chen Wang1
Donghao Zhang1
Dongnan Liu1
Eibe Frank1
Fang Chen1
Heng Wang1
Hui Ma1
Imran Razzak1
Ivan Lee1

Impactful Papers

Papers from Australasian Conference on Artificial Intelligence 2019 that shaped research clusters.

Influential

Papers

Title
AI 2019: Advances in Artificial Intelligence - 32nd Australasian Joint Conference, Adelaide, SA, Australia, December 2-5, 2019, Proceedings
Analyzing the Variation Property of Contextualized Word Representations
An Empirical Study of Reward Structures for Actor-Critic Reinforcement Learning in Air Combat Manoeuvring Simulation
Bayesian Optimisation for Objective Functions with Varying Smoothness
Bayesian Optimization with Discrete Variables
Detection of Compromised Models Using Bayesian Optimization
DINE: A Framework for Deep Incomplete Network Embedding
Efficient 3D Depthwise and Separable Convolutions with Dilation for Brain Tumor Segmentation
Feature Importance for Biomedical Named Entity Recognition
Genetic Programming for Imputation Predictor Selection and Ranking in Symbolic Regression with High-Dimensional Incomplete Data
Genetic Programming with Pareto Local Search for Many-Objective Job Shop Scheduling
Hybrid Words Representation for Airlines Sentiment Analysis
Information-Theoretic Multi-task Learning Framework for Bayesian Optimisation
LumNet: A Deep Neural Network for Lumbar Paraspinal Muscles Segmentation
Memory-Based Explainable Reinforcement Learning
Multi-label Feature Selection Using Particle Swarm Optimization: Novel Initialization Mechanisms
Online K-Means Clustering with Lightweight Coresets
Optimising Pump Scheduling for Water Distribution Networks
Predicting Financial Well-Being Using Observable Features and Gradient Boosting
Predictive Representation Learning in Motif-Based Graph Networks
Semi-Supervised Learning using Siamese Networks
The Futility of Bias-Free Learning and Search
Towards Robust Web Service Composition with Stochastic Service Failures Based on a Genetic Algorithm
WinoFlexi: A Crowdsourcing Platform for the Development of Winograd Schemas