The purpose of the AAAI conference series is to promote research in artificial intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers in AI and its
The purpose of the AAAI conference series is to promote research in artificial intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers in AI and its affiliated disciplines. AAAI-21 is the Thirty-Fifth AAAI Conference on Artificial Intelligence. Like previous AAAI conferences it will feature technical paper presentations, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, all selected according to the highest standards. AAAI-21 will also include additional programs for students and young researchers.
AAAI-21 will be a virtual conference (recorded talks, opportunities to interact electronically). Every presenter will have the option of participating remotely. We will make more information available as it is finalized.
AAAI-21 welcomes submissions reporting research that advances artificial intelligence, broadly conceived. The conference scope includes machine learning (deep learning, statistical learning, etc), natural language processing, computer vision, data mining, multiagent systems, knowledge representation, human-in-the-loop AI, search, planning, reasoning, robotics and perception, and ethics. In addition to fundamental work focused on any one of these areas we expressly encourage work that cuts across technical areas of AI, bridges between AI and a related research area (e.g., neuroscience; cognitive science) or develops AI techniques in the context of important application domains, such as healthcare, sustainability, transportation, and commerce.
The final set of AAAI-21 keywords is available on the AAAI-21 keywords page. This author’s guide for choosing the best keywords describes important considerations in selecting keywords for a paper.
Most papers in AAAI-21 will be part of the “main track”. In addition to typical AI areas, there will be three focus areas within the main track that highlight timely topics. All main track papers will be reviewed according to the same criteria and via the same process. A second track of the conference will focus on AI for Social Impact. Papers in this track will be reviewed according to a different evaluation rubric than papers in the main track. The same reviewing schedule will be followed for all papers.
Focus Areas in the Main Track
Beyond the usual keywords, the AAAI-21 main track will highlight three focus areas. These are (1) Neuro-Symbolic AI; (2) AI Responses to the COVID-19 Pandemic; and (3) AI for Conference Organization and Delivery. The Conference Committee especially encourages submissions in these focus areas, and will highlight these at the conference in separate sessions. Further details are available at the Focus Areas page. Submissions to the focus areas will be overseen by dedicated area chairs but reviewed according to the same standards and procedures as other AAAI technical submissions.
Approaches melding neural and symbolic reasoning are emerging as a hot topic in the AI community. With the huge recent growth in neural methods and AAAI’s deep roots in symbolic approaches, AAAI is uniquely well suited to fostering this conversation. Example topics include, but are not limited to, representation learning over trees, graphs, first-order logic formulas, and other symbolic objects; using intermediate symbolic representations within a neural network; neural network with prior symbolic knowledge, such as constraints, symbolic features; and combining traditional symbolic algorithms along with neural models.
AI Responses to the COVID-19 Pandemic
This focus area will highlight AI solutions in response to the COVID-19 pandemic. Topics include, but are not limited to, efforts to further scientific understanding of the virus and its impact on society; models for spread of the pandemic; approaches leveraging AI to help contain the virus; methods for improving treatment of COVID-19 patients; and mitigations for economic, social or technical challenges arising from the pandemic.
AI for Conference Organization and Delivery
Entirely virtual conferences have suddenly become a reality, creating both the opportunity and need to leverage AI-based technologies to improve attendees’ experiences: e.g., in discovering papers of interest; watching presentations of technical material; engaging with authors in question periods or poster sessions; and interacting with colleagues in virtual “coffee breaks” or other social activities. Furthermore, many technical problems arise in the organization of AI conferences that can be addressed by AI techniques: e.g., matching thousands of reviewers and papers; detecting conflicts; incentivizing reviewers to invest effort; facilitating conversations among reviewers; recommending paper acceptance or rejection; and scheduling and delivering presentations of accepted papers. This focus area will highlight novel approaches for leveraging AI in the organization and delivery of large, electronically mediated conferences like AAAI itself.
Track on AI for Social Impact
As in past years, AAAI-21 will include a Track on AI for Social Impact (AISI). Submissions to this track will be reviewed according to a rubric that emphasizes the fit between the techniques used and a problem of social importance, rather than simply rewarding technical novelty. In particular, reviewers will assess novelty of the AI problem formulation studied; the paper’s engagement with previous literature on the application problem (whether in the AI literature or elsewhere); both novelty of and justification for the proposed solution; quality of evaluation; facilitation of follow-up work; and overall scope and promise for social impact. Further details are available at the AISI page.
mostra di più
febbraio 2 (Martedì) - 9 (Martedì)