Short or position papers of up to 4 pages are also welcome. The program will also include an invited talk from an expert of the field, and a panel composed by AI experts and transportation experts, with the aim of identifying promising areas of work. AAAI, specifically, is a great venue for our workshop because its audience spans many ML and AI communities. Submission site: https://dstc9.dstc.community/paper-submission, Workshop Chairs: Abhinav Rastogi (Google Research, USA, abhirast@google.com), Yun-Nung (Vivian) Chen (National Taiwan University, Taiwan, y.v.chen@ieee.org)Challenge Chair: Chulaka Gunasekara (IBM Research AI, USA, Chulaka.Gunasekara@ibm.com)Publication Chair: Luis Fernando D’Haro (Universidad Politécnica de Madrid, Spain, lfdharo@die.upm.es)Publicity Chair: Seokhwan Kim (Amazon Alexa AI, USA, seokhwk@amazon.com), Supplemental workshop site: https://sites.google.com/dstc.community/dstc9/. Contributions of research results are sought in the following areas of: Due to the diversity of disciplines engaging in this area, related contributions in other fields, are also welcome. Papers must be between 4-8 pages in the AAAI submission format, with the eighth page containing only references. Explainable AI (XAI) attempts to alleviate concerns of transparency, trust and ethics in AI by making them accountable, interpretable and explainable to humans. Papers that introduce new theoretical concepts or methods, help to develop a better understanding of new emerging concepts through extensive experiments, or demonstrate a novel application of these methods to a domain are encouraged. In this workshop we would like to focus on a contrasting approach, to learn the architecture during training. Manuscripts must be submitted as PDF files via EasyChair online submission system.Please keep your paper format according to AAAI Formatting Instructions (two-column format). If it turns out that the architecture is not appropriate for the task, the user must repeatedly adjust the architecture and retrain the network until an acceptable architecture has been obtained. Please refer and submit through the workshop website listed below. Chatbots are their most recent incarnation and have been widely adopted, particularly in the recent COVID-19 pandemic, as sources of information. The workshop will be organized as a full day meeting. We plan to publish the papers accepted in this workshop as a book with Springer in 2021. Make real-time, data-driven decisions that improve marketing campaigns, sales win rates, and […] Sathyanarayanan N. Aakur (Oklahoma State University, USA), Ullas Nambiar (Accenture, India), Imed Zitouni (Google, USA), and Biplav Srivastava (AI Institute, University of South Carolina, USA), Supplemental workshop site: https://sites.google.com/view/deep-dial2021. The submission site can be found on the workshop website. text, images, and videos). This workshop aims to provide a forum for bringing together experts from the different fields of AI to discuss the challenges related to any area of Urban Mobility, from the perspective of how AI techniques can be leveraged to address these challenges and whether novel AI techniques have to be developed. Meta learning and lifelong learning relate to the human ability of continuously learning new tasks with very limited labeled training data. The audience of this workshop will be researchers and students from a wide array of disciplines including, but not limited to, statistics, computer science, economics, public policy, psychology, management, and decision science, who work at the intersection of causal inference, machine learning, and behavior science. Modern encryption techniques such as homomorphic encryption enables doing machine learning on encrypted data directly, meaning nobody has to know what we are doing online. There are expected to be approximately 70-80 attendees. The workshop will be a one-day and a half meeting. If a work is under submission for the main conference as well or for a different conference, it should be written in the title. Moreover, to tackle and overcome several issues in personalized healthcare, information technology will need to evolve to improve communication, collaboration, and teamwork among patients, their families, healthcare communities, and care teams involving practitioners from different fields and specialties. The program of the workshop will include invited talks, spotlight paper presentations, and lightning poster presentations. The workshop supplementary site URL will be available soon. AI Research), Jamin Shin (Riiid! A major problem is that existing clinical AI methods are less trustworthy. This manual extraction process is usually inefficient, error-prone, and inconsistent. Huáscar Espinoza (Commissariat à l´Energie Atomique, France), José Hernández-Orallo (Universitat Politècnica de València, Spain), Cynthia Chen (University of Hong Kong, China), Seán Ó hÉigeartaigh (University of Cambridge, UK), Xiaowei Huang (University of Liverpool, UK), Mauricio Castillo-Effen (Lockheed Martin, USA), Richard Mallah (Future of Life Institute, USA), John McDermid (University of York, UK), Supplemental workshop site: http://safeaiw.org/. Trusted Customer Intelligence Platform Go beyond traditional CDPs. Authors of accepted papers will be invited to deliver a talk, and well-recognized experts of the field will be invited to participate in the panel or to deliver an invited talk. Submission site: https://easychair.org/my/conference?conf=xaiaaai21, Prashan Madumal, Silvia Tulli, David Aha, Rosina Weber, Supplemental workshop site: https://sites.google.com/view/xaiworkshop/topic. This workshop is especially interested in hearing about the challenges and problems data science and AI can address related to the global pandemic, and relevant deployments and experiences in gearing AI to cope with COVID-19. By gathering the leading companies, organizations, and people differently affected by artificial intelligence, PAI establishes a common ground between entities which otherwise may not have cause to work together – and in so doing – serves as a uniting force for good in the AI ecosystem. The deep learning community must often confront serious time and hardware constraints from suboptimal architectural decisions. We invite all the teams who participated in DSTC9 to submit their work to this workshop. Submissions will be assessed based on their novelty, technical quality, significance of impact, interest, clarity, relevance, and reproducibility. Workshop registration is available to AAAI-21 technical registrants at a discounted rate, or separately to workshop only registrants. There has been limited interaction among these subareas on XAI, and even less work has focused on promoting and sharing sound designs, methods, and measures for evaluating the effectiveness of explanations (generated by AI systems) in human subject studies. Among the questions that participants will discuss and seek to answer are: HAI will be a one-day workshop that will include presentations of accepted papers, a talk by an invited speaker and a panel discussion to discuss the above questions. Scientific documents such as research papers, patents, books, or technical reports are one of the most valuable resources of human knowledge. Submissions are anonymous, and must conform to the AAAI-21 instructions for double-blind review. Two types of papers can be submitted. This paper draws upon existing work by academics, labor unions, and other institutions to explain why organizations should prioritize worker well-being. We will organize a one-day workshop, featuring high-profile keynote speakers, a selection of submissions from the workshop, and a panel discussion. The rest of the day will be devoted to the shared task overview and papers. CSKGs come in a wider variety of forms compared to traditional knowledge graphs, ranging from (semi-)structured knowledge graphs, such as ConceptNet, ATOMIC, and FrameNet, to the recent idea to use language models as knowledge graphs. Chatbots have been increasingly used for seeking advice and providing assistance related to symptoms, health facilities and public policies. Submissions are due December 1, 2020. All submissions must be made via EasyChair portal at the following link: https://easychair.org/conferences/?conf=constraint2021, Tanmoy Chakraborty (IIIT Delhi, India, tanmoy@iiitd.ac.in), Steering Committee: Tanmoy Chakraborty (IIIT Delhi, India, tanmoy@iiitd.ac.in), Kai Shu (Illinois Institute of Technology, USA, kshu@iit.edu), H. Russell Bernard (Arizona State University, USA, ufruss@ufl.edu), Huan Liu (Arizona State University, USA, huanliu@asu.edu)Organizing Committee: Tanmoy Chakraborty, IIIT Delhi, tanmoy@iiitd.ac.in), Md Shad Akhtar (IIIT Delhi, shad.akhtar@iiitd.ac.in)Shared Task Organizing Committee: Tanmoy Chakraborty (IIIT Delhi, tanmoy@iiitd.ac.in), Md Shad Akhtar (IIIT Delhi, shad.akhtar@iiitd.ac.in), Asif Ekbal (IIT Patna, asif@iitp.ac.in), Amitava Das (Wipro Research amitava.das2@wipro.com), Supplemental workshop site: http://lcs2.iiitd.edu.in/CONSTRAINT-2021/Twitter handle: @CONSTRAINT_AAAI. AffCon-2021 is the fourth Affective Content Analysis workshop @ AAAI. The workshop will consist of contributed talks, contributed posters, and invited talks on a wide variety of the methods and applications. Papers will be peer-reviewed and selected for oral and/or poster presentation at the workshop. AAAI is pleased to present the AAAI-21 Workshop Program. https://constraint-shared-task-2021.github.io/. The expected attendance is approximately 50 people. In the financial services industry, in particular, a large amount of financial analysts’ work requires knowledge discovery and extraction from different data sources, such as SEC filings, loan documents, industry reports, etc., before the analysts can conduct any analysis. At least one author of each accepted submission must register and present the paper at the workshop. AI for healthcare has emerged into a very active research area in the past few years and has made significant progress. Please follow the AAAI formatting guidelines (https://www.aaai.org/Publications/Templates/AuthorKit20.zip). This workshop will bring together researchers from NLP, computer vision, reasoning and action/robotics to explore end-to-end HAI. Understanding how to best integrate and represent CSKGs, leverage them on a downstream task, and tailor their knowledge to the particularities of the task, are open challenges today. Online hostile posts (e.g., hate speech, fake news, etc.) As deep learning problems become increasingly complex, network sizes must increase and other architectural decisions become critical to success. These form the motivation for the fourth edition of the Workshop on Reasoning and Learning for Human-Machine Dialogues. Data science on IoT data (esp. Meta-Learning is a way to address both issues. The following is an abbreviated excerpt from Acting Executive Director Rebecca Finlay’s opening letter in PAI’s 2020 Annual Report It is impossible to look back on the last year and not think abou... Partnership on AI 2020 Annual Report: Charting a Course Together for Responsible AI. Invited speakers will include Susan Athey, keynote (Economics of Technology, Stanford University, Sendhil Mullainathan, keynote (Computation and Behavioral Science, University of Chicago), Eric Tchetgen Tchetgen (Statistics, University of Pennsylvania), Jon Kleinberg (Computer Science, Cornell University), and Munmun De Choudhury (Interactive Computing, Georgia Tech). “Fairness” defined in machine learning literature often misuses or misunderstands the legal concepts from which they purport to be inspired by. Graph neural networks on node-level, graph-level embedding, Joint learning of graph neural networks and graph structure, Learning representation on heterogeneous networks, knowledge graphs, Deep generative models for graph generation/semantic-preserving transformation, Graph2seq, graph2tree, and graph2graph models, Spatial and temporal graph prediction and generation, Learning and reasoning (machine reasoning, inductive logic programming, theory proving), Natural language processing (information extraction, semantic parsing, text generation), Bioinformatics (drug discovery, protein generation, protein structure prediction), Reinforcement learning (multi-agent learning, compositional imitation learning), Financial security (anti-money laundering), Cybersecurity (authentication graph, Internet of Things, malware propagation), Geographical network modeling and prediction (Transportation and mobility networks, social, Explainable/Interpretable Machine Learning, Fairness, Accountability and Transparency, Interactive Teaching Strategies and Explainability, Constraint satisfaction and programming (CP), (inductive) logic programming (LP and ILP), Learning with Multi-relational graphs (alignment, knowledge graph construction, completion, reasoning with knowledge graphs, etc. The impressive gains of learning-based models to discover insights from data have to be married with pre-known knowledge — e.g., common-sense and spatio-temporal knowledge — to be usable by the common man. Submissions can be full technical papers (up to 8 pages) or short papers (up to 4 pages), and should be formatted in the AAAI style. Researchers from related fields are invited to submit papers on the recent advances, resources, tools, and upcoming challenges for SDU. While existing results are encouraging, not too many clinical AI solutions are deployed in hospitals or actively utilized by physicians. The study of complex graphs is a highly interdisciplinary field that aims to study complex systems by using mathematical models, physical laws, inference and learning algorithms, etc. Tweet Post The workshop will include invited speakers, panels, virtual poster sessions, and presentations. Attendance is open to all. The topics of interest include, but not limited to: Papers will be presented in poster format and some will be selected for oral presentation. Investment currently is strong for numerous types of telehealth systems, many including AI components, and leading enterprises in this work are now recognizing the important need for participatory design. For papers that rely heavily on empirical evaluations, the experimental methods and results should be clear, well executed, and repeatable. Papers more suited for a poster, rather than a presentation, would be invited for a poster session. However, machine learning models face various threats. The AI SPI explores ways to proactively guide AI advancement in the direction of expanding the economic prospects of workers, particularly those with limited opportunities for educational advancement. System reports should also follow the AAAI formatting guidelines and have 4-6 pages including references. However, the use of rich data sets also raises significant privacy concerns: They often reveal personal sensitive information that can be exploited, without the knowledge and/or consent of the involved individuals, for various purposes including monitoring, discrimination, and illegal activities. All submissions should be done electronically via EasyChair. Increased specialization in the sub-fields of AI has led to extreme fragmentation of the field. Although telehealth technology has been present for years, appearance of the Covid-19 pandemic dramatically has accelerated its growth. Representation learning, distributed representations learning and encoding in natural language processing for financial documents; Synthetic or genuine financial datasets and benchmarking baseline models; Transfer learning application on financial data, knowledge distillation as a method for compression of pre- trained models or adaptation to financial datasets; Search and question answering systems designed for financial corpora; Named-entity disambiguation, recognition, relationship discovery, ontology learning and extraction in financial documents; Knowledge alignment and integration from heterogeneous data; Using multi-modal data in knowledge discovery for financial applications. Furthermore, models that are robust to adversarial attacks usually require longer training time and orders of magnitude more computation FLOPs than normal networks. This is no longer the case. System reports will be presented during poster sessions. The accepted papers will beposted on the workshop website and will not appear in the AAAI proceedings. In this workshop, we plan to invite AIEd enthusiasts from all around the world through three different channels. Natural conversation is a hallmark of intelligent systems and thus dialog systems have been a key sub-area of Artificial Intelligence research for decades. In summary, we seek solutions to achieve a wholistic solution for robust, secure and efficient machine learning. It will aim to identify important research directions, opportunities for synthesis and unification of representations and algorithms for recognition. Theoretical contributions of adversarial machine learning. The COVID-19 pandemic has been an opportunity to validate the relevance of collaborative assistance technologies for real-world needs. Possible reasons are that the precision and recall requirements for extracted knowledge to be used in business processes are fastidious, and signals gathered from these knowledge discovery tasks are usually very sparse and thus the generation of supervision signals is quite challenging. Short papers, which describe a position on the topic of the workshop or a demonstration/tool, may be no longer than 4 pages, references included. For training, gradient or weight exchange is necessary for decentralized training, but such exchange requires communication, which may be slow. This is relevant for increasingly decentralized workplaces, asynchronous collaborations, and computer-mediated communication. for causal estimation in the behavior science world. Modeling highly structured data with time-evolving, multi-relational, and multi-modal nature. Papers must be in trouble-free, high-resolution PDF format, formatted for US Letter (8.5″ x 11″) paper, using Type 1 or TrueType fonts. To help fill this gap, the Partnership on AI has initiated Closing Gaps in Responsible AI, a multiphase, multi-stakeholder project aimed at surfacing salient challenges and evaluate potential solutions for organizational implementation of responsible AI. Businesses spend $1.3 trillion on 265 billion customer service calls each year. There is now a great deal of interest in finding better alternatives to this scheme. Niyati Chhaya, Primary Contact (Adobe Research, nchhaya@adobe.com), Kokil Jaidka (Nanyang Technological University, kokil.j@gmail.com ), Jennifer Healey (Adobe Research, jehealey@adobe.com), Lyle Ungar (University of Pennsylvania, ungar@cis.upenn.edu), Atanu R Sinha (Adobe Research, atr@adobe.com). This one-day workshop aims to bring together both academic researchers and industrial practitioners from different backgrounds and perspectives to above challenges. AI Research), Dongmin Shin (Riiid! Topics of interest include, but are not limited to: The workshop will consist of: (1) two keynote talks, (2) a panel discussion on ‘Are language models enough?’, (3) presentations of full, short, and position papers, and (4) a discussion session. The full-day workshop will start with an opening remark followed by long research paper presentations in the morning. To push forward the research on acronym understanding in scientific text, we propose two shared tasks on acronym identification (i.e., recognizing acronyms and phrases in text) and disambiguation (i.e., finding the correct expansion for an ambiguous acronym). Ultimately, better human machine interactions will lead to businesses being able to reinvent and constantly improve the offerings and experiences their customers want. New neural network architectures on graph-structured data have achieved remarkable performance in these tasks when applied to domains such as social networks, bioinformatics and medical informatics. Further, once the model is updated to incorporate newer data distribution or task, the knowledge learnt from the previous task is “forgotten.” Meta learning focuses on designing models that utilize prior knowledge learnt from other tasks to perform a new task. Why Does Explainable AI Matter Anyway? Attendance is virtual and open to all. More recently, due to both data privacy requirements as specified in the European Union’s General Data Protection Regulation (GDPR), and the limitations of computation power, the training process of machine learning models has extended from centralized to decentralized (i.e. Psychological models of affect are adopted by several disciplines to conceptualize and measure users’ opinions, intentions, motives, and expressions. Accepted papers are expected to be presented at the workshop and will be published in the workshop proceedings. As a result, companies usually benefit from the results of AI models without understanding their workflow. Therefore, it is important to identify customers who potentially become unsatisfied and might lead to escalations. A large share of content created are outcomes of collaboration. For example, existing approaches make clinical decisions in a black-box way, which renders the decisions difficult to understand and less transparent. PAI research reveals a gap between explainability in practice and the goals of transparency. Delivering enhanced data and analytical capabilities is an essential element of our journey, and the work completed in partnership with our Risk Consulting team and expert.ai adds to the AXA XL tool kit. We invite the submission of original and high-quality research papers in the relevant fields of misinformation. Modeling complex data that involves mapping between graph-based inputs and other highly structured output data such as sequences, trees, and relational data with missing values. This workshop intends to share visions of investigating new approaches and methods at the intersection of Graph Neural Networks and real-world applications. Topics of interest include but are not limited to: Acronyms, i.e., short forms of long phrases, are common in scientific writing. What is the status of existing approaches in ensuring AI and Machine Learning (ML) safety, and what are the gaps? Submission site: https://cmt3.research.microsoft.com/PPAI2021, Ferdinando Fioretto (Syracuse University), Pascal Van Hentenryck (Georgia Institute of Technology), Richard W. Evans (Rice University), Supplemental workshop site: https://ppai21.github.io/. Submitted papers will be assessed based on their novelty, technical quality, potential impact, and clarity of writing. Following this AAAI conference submission policy, reviews are double-blind, and author names and affiliations should NOT be listed. Many firms miss the chance to implement low complexity and high benefit artificial intelligence use cases. This topic encompasses forms of Neural Architecture Search (NAS) in which the performance properties of each architecture, after some training, are used to guide the selection of the next architecture to be tried. Supplemental workshop site: https://sites.google.com/view/gclr2021/. Complex systems are often characterized by several components that interact in multiple ways among each other. In this workshop, we aim to address the trustworthy issues of clinical AI solutions. SDU will also host a poster session for presenting the short research papers and the system reports of the shared tasks. This one-day workshop intends to bring experts from machine learning, security communities, and federated learning together to work more closely in addressing the posed concerns. We propose explicitly modeling the human explainee via Bayesian Teaching, which evaluates explanations by how much they shift explainees' inferences … We invite participants to submit papers on the 9th of November, based on but not limited to, the following topics: RL in various formalisms: one-shot games, turn-based, and Markov games, partially-observable games, continuous games, cooperative games; deep RL in games; combining search and RL in games; inverse RL in games; foundations, theory, and game-theoretic algorithms for RL; opponent modeling; analyses of learning dynamics in games; evolutionary methods for RL in games; RL in games without the rules; Monte Carlo tree search, online learning in games. 7 pages, including references) and short papers (max. The automated processing of unstructured data to discover knowledge from complex financial documents requires a series of techniques such as linguistic processing, semantic analysis, and knowledge representation and reasoning. The past editions of the workshop were huge successes attracting 100+ AI researchers to discuss a variety of topics. “Authors of accepted regular papers can opt-in to the formal PMLR proceedings. This report documents the serious shortcomings of algorithmic risk assessment tools in the U.S. criminal justice system, and includes ten requirements that jurisdictions should weigh heavily prior to the use of these tools. The knowledge covered in CSKGs varies greatly, spanning procedural, conceptual, and syntactic knowledge, among others. Explainable AI (XAI) attempts to improve human understanding but rarely accounts for how people typically reason about unfamiliar agents. Accepted submissions will have the option of being published on the workshop website. They need to enter into a dialog and convincingly explain their suggestions and decision-making behavior. The list of possible topics includes, but is not limited to: fake news and hate speech detection in regional languages or code-mixed/code-switched environment; evolution of fake news and hate speech; early detection for hostile posts; claim detection and verification related to misinformation; psychological study of the users/spreaders of hostile posts; hate speech normalization; hesource/tool creation for combating hostile posts. Games provide an abstract and formal model of environments in which multiple agents interact: each player has a well-defined goal and rules to describe the effects of interactions among the players. Hyperparameters such as the number of layers, the number of nodes in each layer, the pattern of connectivity, and the presence and placement of elements such as memory cells, recurrent connections, and convolutional elements are all manually selected. Balaraman Ravindran, Chair (Indian Institute of Technology Madras, India, ravi@cse.iitm.ac.in), Kristian Kersting (TU Darmstadt, Germany, kersting@cs.tu-darmstadt.de), Sarika Jalan (Indian Institute of Technology Indore, India, sarika@iiti.ac.in), Partha Pratim Talukdar (Indian Institute of Science, India, ppt@iisc.ac.in), Sriraam Natarajan (University of Texas Dallas, USA, Sriraam.Natarajan@utdallas.edu), Tarun Kumar (Indian Institute of Technology Madras, India, tkumar@cse.iitm.ac.in), Deepak Maurya (Indian Institute of Technology Madras, India, maurya@cse.iitm.ac.in), Nikita Moghe (The University of Edinburgh, UK, nikita.moghe@ed.ac.uk), Naganand Yadati (Indian Institute of Science, India, y.naganand@gmail.com), Jeshuren Chelladurai (Indian Institute of Technology Madras, India, jeshurench@gmail.com), Aparna Rai (Indian Institute of Technology Guwahati, India, raiaparna13@gmail.com). The final schedule will be available in October. We invite submission from participants who can contribute to the theory and applications of modeling complex graph structures such as hypergraphs, multilayer networks, multi-relational graphs, heterogeneous information networks, multi-modal graphs, signed networks, bipartite networks, temporal / dynamic graphs, etc. The workshop is open to all researchers, academicians, and industry personnel working in the relevant field.