Keywords and Subtopics

Focus Area: Neuro-Symbolic AI (NSAI)
Focus Area: AI Responses to the COVID-19 Pandemic (Covid19)
Focus Area: AI for Conference Organization and Delivery (AICOD)
Cognitive Modeling & Cognitive Systems (CMS)

  • CMS: Adaptive Behavior
  • CMS: Affective Computing
  • CMS: Agent Architectures
  • CMS: Analogy
  • CMS: Bayesian Learning
  • CMS: Cognitive Architectures
  • CMS: Computational Creativity
  • CMS: Conceptual Inference and Reasoning
  • CMS: Introspection and Meta-Cognition
  • CMS: Memory Storage And Retrieval
  • CMS: Neural Spike Coding
  • CMS: Simulating Humans
  • CMS: Social Cognition And Interaction
  • CMS: Structural Learning And Knowledge Capture
  • CMS: Symbolic Representations
  • CMS: Other Foundations of Cognitive Modeling & Systems
  • CMS: Applications

Computer Vision (CV)

  • CV: 3D Computer Vision
  • CV: Adversarial Attacks & Robustness
  • CV: Biology & Cell microscopy
  • CV: Biometrics, Face, Gesture & Pose
  • CV: Computational Photography, Image & Video Synthesis
  • CV: Ethics — Bias, Fairness, Transparency & Privacy
  • CV: Image and Video Retrieval
  • CV: Language and Vision
  • CV: Learning & Optimization for CV
  • CV: Low Level & Physics-based Vision
  • CV: Motion & Tracking
  • CV: Multi-modal Vision
  • CV: Object Detection & Categorization
  • 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: Satisfiability Modulo Theories
  • 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: Conversational Systems for Recommendation & Retrieval
  • DMKM: Data Compression
  • DMKM: Data Stream Mining
  • DMKM: Data Visualization & Summarization
  • DMKM: Graph Mining, Social Network Analysis & Community Mining
  • DMKM: Intelligent Query Processing
  • DMKM: Knowledge Acquisition from the Web
  • 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 & Collaborative Filtering
  • DMKM: Representing, Reasoning, and Using Provenance, Trust, Privacy, and Security on the Web
  • DMKM: Rule Mining & Pattern Mining
  • DMKM: Scalability, Parallel & Distributed Systems
  • DMKM: Semantic Web
  • DMKM: Web Ontologies — Creation, Extraction, Evolution, Mapping, Merging, and Alignment. Tags and Folksonomies
  • DMKM: Web Personalization & User Modeling
  • DMKM: Web Search & Information Retrieval
  • DMKM: Web Spam Detection
  • 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: General Game Playing
  • GTEP: Mechanism Design
  • GTEP: Imperfect Information
  • GTEP: Negotiation and Contract-Based Systems
  • GTEP: Opponent Modeling
  • GTEP: Security Games
  • GTEP: Social Choice / Voting
  • GTEP: Other Foundations of Game Theory & Economic Paradigms
  • GTEP: Applications

Human-Computation and Crowd Sourcing (HCC)

  • HCC: AI for Web-Based Collaboration and Cooperation
  • HCC: Analysis of Human Computation (Limitations, Optimality)
  • HCC: Collaborative vs. Competitive Tasks
  • HCC: Design of Novel Tasks/Workflows
  • HCC: Game-Theoretic Analysis & Mechanism Design
  • HCC: Human Computation Games and Captchas
  • HCC: Labeling/Active Learning with Imperfect Human Labelers
  • HCC: Learning of Cost, Reliability, and Skill of Labelers/Tasks
  • HCC: Programming Languages, Tools, and Platforms
  • HCC: Social Networks & Social Credit in Human Computation
  • HCC: Task Allocation
  • HCC: Taxonomy of Human Computation Tasks
  • HCC: Theory & Practice of User Engagement and Joint Decision Making
  • HCC: Other Foundations of Human Computation & Crowdsourcing
  • HCC: Applications

Humans and AI (HAI)

  • HAI: Brain-Sensing and Analysis
  • HAI: Communication Protocols
  • HAI: Emotional Intelligence
  • HAI: Game Design — Procedural Content Generation & Storytelling
  • HAI: Game Design — Virtual Humans, NPCs and Autonomous Characters
  • HAI: Human-Agent Negotiation
  • HAI: Human-Aware Planning and Behavior Prediction
  • HAI: Human-Computer Interaction
  • HAI: Human-in-the-loop Machine Learning
  • HAI: Intelligent User Interfaces
  • HAI: Interaction Techniques and Devices
  • HAI: Language Acquisition
  • HAI: Learning Human Values and Preferences
  • HAI: Planning and Decision Support for Human-Machine Teams
  • HAI: Teamwork, Team formation
  • HAI: Understanding People, Theories, Concepts and Methods
  • HAI: User Experience and Usability
  • HAI: Voting
  • HAI: Other Foundations of Humans & AI
  • HAI: 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
  • 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: Bayesian Learning
  • ML: Bio-inspired Learning
  • ML: Calibration & Uncertainty Quantification
  • ML: Causal Learning
  • ML: Classification and Regression
  • ML: Clustering
  • ML: (Deep) Neural Network Algorithms
  • ML: (Deep) Neural Network Learning Theory
  • ML: Dimensionality Reduction/Feature Selection
  • ML: Distributed Machine Learning & Federated Learning
  • ML: Ethics — Bias, Fairness, Transparency & Privacy
  • ML: Ensemble Methods
  • ML: Evaluation and Analysis (Machine Learning)
  • ML: Evolutionary Learning
  • ML: Feature Construction/Reformulation
  • ML: Graph-based Machine Learning
  • ML: Hyperparameter Tuning / Algorithm Configuration
  • ML: Imitation Learning & Inverse Reinforcement Learning
  • ML: Kernel Methods
  • ML: Learning on the Edge & Model Compression
  • ML: Learning with Manifolds
  • ML: Learning Preferences or Rankings
  • ML: Learning Theory
  • ML: Matrix & Tensor Methods
  • ML: Multi-class/Multi-label Learning & Extreme Classification
  • ML: Multi-instance/Multi-view Learning
  • ML: Multimodal Learning
  • ML: Neural Generative Models & Autoencoders
  • ML: Online Learning & Bandits
  • ML: Optimization
  • ML: Probabilistic Graphical Models
  • ML: Quantum Machine Learning
  • ML: Reinforcement Learning
  • ML: Relational Learning
  • ML: Representation Learning
  • ML: Scalability of ML Systems
  • ML: Semi-Supervised Learning
  • ML: Structured Prediction
  • ML: Time-Series/Data Streams
  • ML: Transfer/Adaptation/Multi-task/Meta/Automated Learning
  • 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: Evaluation and Analysis (Multiagent Systems)
  • MAS: Mechanism Design
  • MAS: Multiagent Learning
  • MAS: Multiagent Planning
  • MAS: Modeling other Agents
  • MAS: Teamwork
  • MAS: Multiagent Systems under Uncertainty
  • MAS: Other Foundations of Multi Agent Systems
  • MAS: Applications

Philosophy and Ethics of AI (PEAI)

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

Planning, Routing, and Scheduling (PRS)

  • PRS: Activity and Plan Recognition
  • PRS: Control of High-Dimensional Systems
  • PRS: Deterministic Planning
  • PRS: Planning with Markov Models (MDPs, POMDPs)
  • PRS: Mixed Discrete/Continuous Planning
  • PRS: Model-Based Reasoning
  • PRS: Optimization of Spatio-temporal Systems
  • PRS: Plan Execution and Monitoring
  • PRS: Planning/Scheduling and Learning
  • PRS: Planning under Uncertainty
  • 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: Stochastic Models & Probabilistic Inference
  • RU: Relational Probabilistic Models
  • RU: Sequential Decision Making
  • RU: Stochastic Optimization
  • RU: Uncertainty Representations
  • RU: Other Foundations of Reasoning under Uncertainty
  • RU: Applications

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: Multimodal Perception & Sensor Fusion
  • ROB: Multi-Robot Systems
  • ROB: State Estimation
  • ROB: Other Foundations of Intelligent Robots
  • ROB: 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: Conversational AI/Dialog Systems
  • SNLP: Discourse, Pragmatics & Argument Mining
  • SNLP: Ethics — Bias, Fairness, Transparency & Privacy
  • SNLP: Generation
  • SNLP: Information Extraction
  • SNLP: Interpretaility & Analysis of NLP Models
  • SNLP: Language Grounding & Multi-modal NLP
  • 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: Speech & Signal Processing
  • SNLP: Speech Synthesis
  • SNLP: Stylistic Analysis & Text Mining
  • SNLP: Summarization
  • SNLP: Syntax — Tagging, Chunking & Parsing
  • SNLP: Text Classification & Sentiment Analysis
  • 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
An Authors’ Guide to Choosing the Best Keyword(s) in AAAI Main Track

An Authors’ Guide to Choosing the Best Keyword(s) in AAAI 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-21 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 help us to find your paper the most appropriate reviewers. A secondary objective (upon acceptance) is to help us to schedule related papers together into sessions. We focus on the primary objective here, imagining that it is more important to most authors. (We do want to note that we will use a variety of other signals beyond keywords to match reviewers and papers, so not everything hinges on this choice.)

The main principle for choosing your 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 expert in that subarea will be positioned to evaluate the paper most effectively.

Most of the time, we recommend starting with the top-level area (e.g., vision, knowledge representation, etc) that describes the paper’s methodological focus and then picking the closest fit keyword in that area.

But of course there are exceptions. First, consider the three focus areas. If you feel that your paper is a close fit to one of these, we recommend signaling this through your choice of primary keyword.

Second, a sizeable number of papers 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: Ethics — Bias, Fairness, Transparency & Privacy” as the primary area (since healthcare is the application component). A crowdsourcing mechanism design paper could use “HCC: Mechanism Design in Human Computation”, as such a joint keyword exists.

(4) However, perhaps you feel that no keyword adequately captures the intersection of AI fields to which the paper makes its primary contribution. In such cases, you face a judgment call about which community is likely to best appreciate your 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 (or the focus area of neuro-symbolic AI) will be better fits.

Now let us consider secondary keywords. In making this choice, it is helpful to consider two questions. First, all things being equal, what beyond my primary keyword would I like my reviewers to be expert in? Second, if no one reviewer is likely to tick all the boxes, how would I describe experts outside the primary subarea who would add important perspectives to my paper’s review? 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 & Security” and “APP: Games”.

We will make every attempt to find reviewers that cover all keywords you specify. 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 your 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 primary keywords will understand the paper, assuming they have broad (but not deep) knowledge of other fields of AI.

In the end, choosing the best keywords is an art; making poor choices about keywords can increase your chance of getting suboptimal reviews. We hope that this guide helps you to understand the reasoning process a little bit and that, with your help, we’re able to do the best job possible of matching papers with qualified reviewers.

Mausam & Kevin Leyton-Brown
AAAI-2021 Program Co-chairs

This site is protected by copyright and trademark laws under US and International law. All rights reserved. Copyright © 1995–2021 AAAI