Sponsored by the Association for the Advancement of Artificial Intelligence

The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22)

AAAI-23 Keywords

Submission Groups

Cognitive Modeling & Cognitive Systems (CMS)
Computer Vision (CV)
Constraint Satisfaction and Optimization (CSO)
Data Mining & Knowledge Management (DMKM)
Game Theory and Economic Paradigms (GTEP)
Humans and AI (HAI)
Intelligent Robotics (ROB)
Knowledge Representation and Reasoning (KRR)
Machine Learning (ML)
Multiagent Systems (MAS)
Philosophy and Ethics of AI (PEAI)
Planning, Routing, and Scheduling (PRS)
Reasoning under Uncertainty (RU)
Search and Optimization (SO)
Speech & Natural Language Processing (SNLP)
Domain(s) of Application (APP)

Keywords and Subtopics

Cognitive Modeling & Cognitive Systems (CMS)

CMS: Adaptive Behavior
CMS: Affective Computing
CMS: Agent & Cognitive Architectures
CMS: Analogical and Conceptual Reasoning
CMS: Bayesian Learning
CMS: Brain modeling
CMS: Computational Creativity
CMS: Introspection and Meta-Cognition
CMS: Memory Storage And Retrieval
CMS: Simulating Humans
CMS: Social Cognition and Interaction
CMS: Structural Learning and Knowledge Capture
CMS: Other Foundations of Cognitive Modeling & Systems
CMS: Applications

Computer Vision (CV)

CV: 3D Computer Vision
CV: Adversarial Attacks & Robustness
CV: Bias, Fairness & Privacy
CV: Biometrics, Face, Gesture & Pose
CV: Computational Photography, Image & Video Synthesis
CV: Image and Video Retrieval
CV: Interpretability and Transparency
CV: Language and Vision
CV: Learning & Optimization for CV
CV: Low Level & Physics-based Vision
CV: Medical and Biological Imaging
CV: Motion & Tracking
CV: Multi-modal Vision
CV: Object Detection & Categorization
CV: Representation Learning for Vision
CV: Scene Analysis & Understanding
CV: Segmentation
CV: Video Understanding & Activity Analysis
CV: Vision for Robotics & Autonomous Driving
CV: Visual Reasoning & Symbolic Representations
CV: Other Foundations of Computer Vision
CV: Applications

Constraint Satisfaction and Optimization (CSO)

CSO: Constraint Learning and Acquisition
CSO: Constraint Optimization
CSO: Constraint Programming
CSO: Constraint Satisfaction
CSO: Distributed CSP/Optimization
CSO: Mixed Discrete/Continuous Optimization
CSO: Satisfiability
CSO: Search
CSO: Solvers and Tools
CSO: Other Foundations of Constraint Satisfaction & Optimization
CSO: Applications

Data Mining & Knowledge Management (DMKM)

DMKM: Anomaly/Outlier Detection
DMKM: Data Compression
DMKM: Data Stream Mining
DMKM: Data Visualization & Summarization
DMKM: Graph Mining, Social Network Analysis & Community Mining
DMKM: Linked Open Data, Knowledge Graphs & KB Completion
DMKM: Mining of Spatial, Temporal or Spatio-Temporal Data
DMKM: Mining of Visual, Multimedia & Multimodal Data
DMKM: Recommender Systems
DMKM: Rule Mining & Pattern Mining
DMKM: Scalability, Parallel & Distributed Systems
DMKM: Semantic Web
DMKM: Web Personalization & User Modeling
DMKM: Web Search & Information Retrieval
DMKM: Web-based QA
DMKM: Other Foundations of Data Mining & Knowledge Management
DMKM: Applications

Game Theory and Economic Paradigms (GTEP)

GTEP: Adversarial Learning
GTEP: Auctions and Market-Based Systems
GTEP: Behavioral Game Theory
GTEP: Computational Simulations
GTEP: Cooperative Game Theory
GTEP: Coordination and Collaboration
GTEP: Equilibrium
GTEP: Fair Division
GTEP: Game Theory
GTEP: Imperfect Information
GTEP: Mechanism Design
GTEP: Negotiation and Contract-Based Systems
GTEP: Social Choice / Voting
GTEP: Other Foundations of Game Theory & Economic Paradigms
GTEP: Applications

Humans and AI (HAI)

HAI: Brain-Sensing and Analysis
HAI: Communication Protocols
HAI: Crowdsourcing
HAI: Emotional Intelligence
HAI: Games, Virtual Humans, and Autonomous Characters
HAI: Human Computation
HAI: Human-Agent Negotiation
HAI: Human-Aware Planning and Behavior Prediction
HAI: Human-Computer Interaction
HAI: Human-in-the-loop Machine Learning
HAI: Human-Machine Teams
HAI: Language Acquisition
HAI: Learning Human Values and Preferences
HAI: Procedural Content Generation & Storytelling
HAI: Other Foundations of Humans & AI
HAI: Applications

Intelligent Robotics (ROB)

ROB: Behavior Learning & Control
ROB: Cognitive Robotics
ROB: Human-Robot Interaction
ROB: Learning & Optimization for ROB
ROB: Localization, Mapping, and Navigation
ROB: Manipulation
ROB: Motion and Path Planning
ROB: Multi-Robot Systems
ROB: Multimodal Perception & Sensor Fusion
ROB: State Estimation
ROB: Other Foundations of Intelligent Robots
ROB: Applications

Knowledge Representation and Reasoning (KRR)

KRR: Action, Change, and Causality
KRR: Argumentation
KRR: Automated Reasoning and Theorem Proving
KRR: Belief Change
KRR: Case-Based Reasoning
KRR: Common-Sense Reasoning
KRR: Computational Complexity of Reasoning
KRR: Description Logics
KRR: Diagnosis and Abductive Reasoning
KRR: Geometric, Spatial, and Temporal Reasoning
KRR: Knowledge Acquisition
KRR: Knowledge Engineering
KRR: Knowledge Representation Languages
KRR: Logic Programming
KRR: Nonmonotonic Reasoning
KRR: Ontologies and Semantic Web
KRR: Preferences
KRR: Qualitative Reasoning
KRR: Reasoning with Beliefs
KRR: Other Foundations of Knowledge Representation & Reasoning
KRR: Applications

Machine Learning (ML)

ML: Active Learning
ML: Adversarial Learning & Robustness
ML: Auto ML and Hyperparameter Tuning
ML: Bayesian Learning
ML: Bias and Fairness
ML: Bio-inspired Learning
ML: Calibration & Uncertainty Quantification
ML: Causal Learning
ML: Classification and Regression
ML: Clustering
ML: Deep Generative Models & Autoencoders
ML: Deep Learning Theory
ML: Deep Neural Architectures
ML: Deep Neural Network Algorithms
ML: Dimensionality Reduction/Feature Selection
ML: Distributed Machine Learning & Federated Learning
ML: Ensemble Methods
ML: Evaluation and Analysis (Machine Learning)
ML: Evolutionary Learning
ML: Graph-based Machine Learning
ML: Imitation Learning & Inverse Reinforcement Learning
ML: Kernel Methods
ML: Learning on the Edge & Model Compression
ML: Learning Preferences or Rankings
ML: Learning Theory
ML: Lifelong and Continual Learning
ML: Matrix & Tensor Methods
ML: Meta Learning
ML: Multi-class/Multi-label Learning & Extreme Classification
ML: Multi-instance/Multi-view Learning
ML: Multimodal Learning
ML: Online Learning & Bandits
ML: Optimization
ML: Privacy-Aware ML
ML: Probabilistic Methods
ML: Quantum Machine Learning
ML: Reinforcement Learning Algorithms
ML: Reinforcement Learning Theory
ML: Relational Learning
ML: Representation Learning
ML: Scalability of ML Systems
ML: Semi-Supervised Learning
ML: Time-Series/Data Streams
ML: Transfer, Domain Adaptation, Multi-Task Learning
ML: Transparent, Interpretable, Explainable ML
ML: Unsupervised & Self-Supervised Learning
ML: Other Foundations of Machine Learning
ML: Applications

Multiagent Systems (MAS)

MAS: Adversarial Agents
MAS: Agent Communication
MAS: Agent-Based Simulation and Emergent Behavior
MAS: Agent/AI Theories and Architectures
MAS: Agreement, Argumentation & Negotiation
MAS: Coordination and Collaboration
MAS: Distributed Problem Solving
MAS: Mechanism Design
MAS: Modeling other Agents
MAS: Multiagent Learning
MAS: Multiagent Planning
MAS: Multiagent Systems under Uncertainty
MAS: Other Foundations of Multiagent Systems
MAS: Applications

Philosophy and Ethics of AI (PEAI)

PEAI: Accountability
PEAI: AI and Epistemology
PEAI: AI and Jobs/Labor
PEAI: AI and Law, Justice, Regulation & Governance
PEAI: Artificial General Intelligence
PEAI: Bias, Fairness & Equity
PEAI: Consciousness and Philosophy of Mind
PEAI: Interpretability and Explainability
PEAI: Morality and Value-based AI
PEAI: Philosophical Foundations of AI
PEAI: Privacy and Security
PEAI: Robot Rights
PEAI: Safety, Robustness & Trustworthiness
PEAI: Societal Impact of AI
PEAI: Other Foundations of Philosophy and Ethics of AI
PEAI: Applications

Planning, Routing, and Scheduling (PRS)

PRS: Activity and Plan Recognition
PRS: Control of High-Dimensional Systems
PRS: Deterministic Planning
PRS: Mixed Discrete/Continuous Planning
PRS: Model-Based Reasoning
PRS: Optimization of Spatio-temporal Systems
PRS: Plan Execution and Monitoring
PRS: Planning under Uncertainty
PRS: Planning with Markov Models (MDPs, POMDPs)
PRS: Planning/Scheduling and Learning
PRS: Replanning and Plan Repair
PRS: Routing
PRS: Scheduling
PRS: Scheduling under Uncertainty
PRS: Temporal Planning
PRS: Other Foundations of Planning, Routing & Scheduling
PRS: Applications

Reasoning under Uncertainty (RU)

RU: Bayesian Networks
RU: Causality
RU: Decision/Utility Theory
RU: Graphical Model
RU: Probabilistic Programming
RU: Relational Probabilistic Models
RU: Sequential Decision Making
RU: Stochastic Models & Probabilistic Inference
RU: Stochastic Optimization
RU: Uncertainty Representations
RU: Other Foundations of Reasoning under Uncertainty
RU: Applications

Search and Optimization (SO)

SO: Adversarial Search
SO: Algorithm Configuration
SO: Algorithm Portfolios
SO: Distributed Search
SO: Evaluation and Analysis
SO: Evolutionary Computation
SO: Heuristic Search
SO: Local Search
SO: Metareasoning and Metaheuristics
SO: Mixed Discrete/Continuous Search
SO: Runtime Modeling
SO: Sampling/Simulation-based Search
SO: Other Foundations of Search & Optimization
SO: Applications

Speech & Natural Language Processing (SNLP)

SNLP: Adversarial Attacks & Robustness
SNLP: Bias, Fairness, Transparency & Privacy
SNLP: Conversational AI/Dialogue Systems
SNLP: Discourse, Pragmatics & Argument Mining
SNLP: Generation
SNLP: Information Extraction
SNLP: Interpretability & Analysis of NLP Models
SNLP: Language Grounding
SNLP: Language Models
SNLP: Learning & Optimization for SNLP
SNLP: Lexical & Frame Semantics, Semantic Parsing
SNLP: Machine Translation & Multilinguality
SNLP: Ontology Induction from Text
SNLP: Phonology, Morphology, Word Segmentation
SNLP: Psycholinguistics and Language Learning
SNLP: Question Answering
SNLP: Sentence-level semantics and Textual Inference
SNLP: Sentiment Analysis and Stylistic Analysis
SNLP: Speech and Multimodality
SNLP: Summarization
SNLP: Syntax — Tagging, Chunking & Parsing
SNLP: Text Classification
SNLP: Text Mining
SNLP: Other Foundations of Speech & Natural Language Processing
SNLP: Applications

Domain(s) of Application (APP)

APP: Accessibility
APP: Art/Music/Creativity
APP: Bioinformatics
APP: Biometrics
APP: Building Design & Architecture
APP: Business/Marketing/Advertising/E-commerce
APP: Cloud
APP: Communication
APP: Design
APP: Economic/Financial
APP: Education
APP: Energy, Environment & Sustainability
APP: Entertainment
APP: Games
APP: Healthcare, Medicine & Wellness
APP: Humanities & Computational Social Science
APP: Internet of Things, Sensor Networks & Smart Cities
APP: Misinformation & Fake News
APP: Mobility, Driving & Flight
APP: Natural Sciences
APP: Security
APP: Social Networks
APP: Software Engineering
APP: Transportation
APP: Web
APP: Other Applications

Choosing the best keyword(s) in the AAAI-23 Main Track

AAAI is a broad-based AI conference, inviting papers from different subcommunities of the field. It also encourages papers that combine different areas of research (e.g., vision and language; machine learning and planning). Finally, it also invites methodological papers focused on diverse areas of application such as healthcare or transportation.

In AAAI-23 authors are asked to choose one primary keyword (mandatory) and (optionally) up to five secondary keywords. With 300 keywords available to choose from, picking the best keywords for a paper may become confusing. This brief guide describes some high-level principles for choosing the best keywords.

The main purpose of keywords is to enable finding the most appropriate reviewers for each submission, which is what this guide focuses on. Note, however, that there are a variety of other signals beyond keywords to match reviewers and papers, so not everything hinges on this choice.

In the end, choosing the best keywords is an art; making poor choices about keywords can increase your chance of getting suboptimal reviews. This guide aims to help authors understand the reasoning process to allow for the best possible matching of papers with qualified reviewers.

Choosing the primary keyword

The main principle for choosing a paper’s primary keyword is to identify the subarea to which the paper makes its main contribution. It should follow that a reviewer who is an expert in that subarea will be positioned to evaluate the paper most effectively.

Most of the time, it is recommended to start with the top-level area (e.g., computer vision, knowledge representation) that describes the paper’s methodological focus and then picking the best fitting keyword in that area.
However, a sizable number of papers describe work at the intersection of different fields. To give some examples, consider papers:

developing general machine learning methods but primarily motivated by problems in NLP
studying bias in machine learning models applied to healthcare
designing a novel elicitation mechanism for crowdsourcing
combining different methodological subareas of AI in an integrated way, e.g., combine learning for solving satisfiability problems.

In all such settings, it becomes trickier to choose the best primary keyword. Here are some rules of thumb:

(1) Focus on where the primary contribution lies, and which community will benefit the most from reading the paper. For example, if an ML algorithm is demonstrated on both computer vision and NLP applications, it is best kept under ML (as it is a general advance, with NLP and vision serving only as applications). If, however, the paper is heavily motivated by details of a particular class of ML problems (e.g., proposing an algorithm that leverages specific structure of images, or language) then picking a keyword that focuses on this class of problems (vision; NLP) is more appropriate.

(2) For papers with specific applications (e.g., healthcare or transportation), typically the application is NOT the primary keyword. Usually, a AAAI main track paper will make methodological advances leading to an impact to an application. Choose a primary keyword based on the methodology. There is one exception to this rule: if the impact to the application area is much more impressive than the methodological innovation, your paper may have the best chance with the application area being the primary keyword. That said, you should carefully consider whether such a paper is more appropriate to submit to the track on AI for Social Impact or to IAAI; note that each of these evaluates papers according to different criteria than the AAAI main track.

(3) For papers genuinely at the intersection of different fields, carefully scan all keywords. It is possible that a joint keyword already exists in the list. For example, an ML paper studying bias applied to healthcare may naturally use the keyword “ML: Bias and Fairness” as the primary area (since healthcare is the application component).

(4) However, perhaps no keyword adequately appears to capture the intersection of AI fields to which the paper makes its primary contribution. In such cases, a judgment call is necessary about which community is likely to best appreciate the work. For example, if a paper combines learning to solve satisfiability problems by using ideas of machine learning within a satisfiability algorithm, it is likely that the paper’s most fundamental impact will be on the design of satisfiability solvers rather than on the design of new learning algorithms; hence, “CSO: Satisfiability” would be a good choice for the primary keyword. However, if the paper is about solving the satisfiability problem using a deep neural network with significant innovations in machine learning, then a machine learning keyword will be a better fit.

Choosing secondary keywords

When choosing secondary keywords, it is helpful to consider two questions. First, all things being equal, what beyond the primary keyword should the reviewers be expert in? Second, if no one reviewer is likely to tick all the boxes, how would experts outside the primary subarea who would add important perspectives to the paper’s review be described? For example, ML fairness applied to healthcare should choose “APP: Healthcare, Medicine & Wellness” as a secondary keyword. Use of machine learning for satisfiability should choose the other area as the secondary keyword.

As an extreme example, if mixed discrete-continuous search is used to solve a routing problem that arises when considering privacy issues in a navigation-based game, with the main contribution being to the routing problem (i.e., “PRS: Routing” is the primary keyword), then the paper may benefit from having multiple secondary keywords “SO: Mixed Discrete/Continuous Search“, “PEAI: Privacy and Security” and “APP: Games”.

Every attempt is made to find reviewers that cover all specified keywords. In some cases it will be hard — such reviewers may not exist, and each reviewer can only review a limited number of papers. On the other hand, be careful what you wish for: adding secondary keywords can be a double-edged sword. If the paper’s contributions are relatively simple from the point of view of an expert in a secondary keyword, then that expert may give a poor rating, perhaps overlooking the paper’s value in another domain. In such situations, it is better to avoid adding secondary keywords as long as experts in the primary keyword will understand the paper, assuming they have broad (but not deep) knowledge of other fields of AI.