Track 2 focuses on the state of the art advances in the computational jobs marketplace. However, most models and AI systems are built with conservative operating environment assumptions due to regulatory compliance concerns. 1145/3394486.3403221. Registration Opens: Feb 02 '22 02:00 PM UTC: Registration Cancellation Refund Deadline: Apr 18 '22(Anywhere on Earth) Paper Submissions Abstract Submission Deadline: Sep 29 '21 12:00 AM UTC: Paper Submission deadline: Oct 06 '21 12:00 AM . Data science is the practice of deriving insights from data, enabled by statistical modeling, computational methods, interactive visual analysis, and domain-driven problem solving. Continuous refinement of AI models using active/online learning. Jos Miguel Hernndez-Lobato, University of CambridgeProf. It highlights the importance of declarative languages that enable such integration for covering multiple formalisms at a high-level and points to the need for building a new generation of ML tools to help domain experts in designing complex models where they can declare their knowledge about the domain and use data-driven learning models based on various underlying formalisms. As deep learning problems become increasingly complex, network sizes must increase and other architectural decisions become critical to success. While progress has been impressive, we believe we have just scratched the surface of what is capable, and much work remains to be done in order to truly understand the algorithms and learning processes within these environments. OARS-KDD2022: KDD 2022 Workshop on Online and Adaptive Recommender Systems Washington DC, DC, United States, August 15, 2022 Topics: data science artificial intelligence recommender system recommendation KDD 2022 Workshop on Online and Adaptive Recommender Systems (OARS) Call For Papers ================== This workshop aims to discuss important topics about adversarial ML to deepen our understanding of ML models in adversarial environments and build reliable ML systems in the real world. If you are interested, please send a short email to rl4edorg@gmail.com and we can add you to the invitee list. In recent months/years, major global shifts have occurred across the globe triggered by the Covid pandemic. 507-516, Singapore, Nov 2017. This is especially the case for non-traditional online resources such as social networks, blogs, news feed, twitter posts, and online communities with the sheer size and ever-increasing growth and change rate of their data. By entering your email, you consent to receive communications from UdeM. KDD 2022. of London). Modeling Health Stage Development of Patients with Dynamic Attributed Graphs in Online Health Communities. Chen Ling, Hengning Cao, Liang Zhao. ), The workshop will be organized as half-day event with 2 invited speakers, follow by presentation from accepted papers (both ordinary papers, and shared task paper). Participants will be given access to publicly available datasets and will be asked to use tools from AI and ML to generate insight from the data. in Proceedings of the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2019), research track (acceptance rate: 14.2%), accepted, Alaska, USA, Aug 2019. December 2020, July 21: Clarified that the workshop this year will be held, June 20: Paper notification is now extended to, Paper reviews are underway! References will not count towards the page limit. Short or position papers of up to 4 pages are also welcome. Manuscripts must be submitted as PDF files viaEasyChair online submission system. The role of adjacent fields of study (e.g, computational social science) in mitigating issues of bias and trust in AI. Optimal transport-based machine learning paradigms; Trustworthy machine learning from the perspective of optimal transport. Rather than studying robustness with respect to particular ML algorithms, our approach will be to explore robustness assurance at the system architecture level, during both development and deployment, and within the human-machine teaming context. Furthermore, leveraging AI to connect disparate social networks amongst teachers \\cite{karimi2020towards}, we may be able to provide greater resources for their planning, which have been shown to significantly affect students achievement. [Best Paper Award]. . Call for Participation The 3rd KDD Workshop on Data-driven Humanitarian Mapping and Policymaking solicits research papers, case studies, vision papers, software demos, and extended abstracts. 2020. Attendance is open to all registered participants. Out of these, around 20~30 papers are accepted. ACM, New York, NY, USA, 10 pages. Submissions are due by 12 November 2021. IEEE, 2014. The accepted papers are allowed to be submitted to other conference venues. Balaraman Ravindran (Indian Institute of Technology Madras, India ravi@cse.iitm.ac.in), Balaraman Ravindran (Indian Institute of Technology Madras, India Primary contact (ravi@cse.iitm.ac.in), Kristian Kersting (TU Darmstadt, Germany, kersting@cs.tu-darmstadt.de), Sriraam Natarajan (Univ of Texas Dallas, USA, Sriraam.Natarajan@utdallas.edu), Ginestra Bianconi (Queen Mary University of London, UK, ginestra.bianconi@gmail.com), Philip S. Chodrow (University of California, Los Angeles, USA, phil@math.ucla.edu) Tarun Kumar (Indian Institute of Technology Madras, India, tkumar@cse.iitm.ac.in), Deepak Maurya (Purdue University, India, maurya@cse.iitm.ac.in), Shreya Goyal (Indian Institute of Technology Madras, India, Goyal.3@iitj.ac.in), Workshop URL:https://sites.google.com/view/gclr2022/. System reports will be presented during poster sessions. In light of these issues, and the ever-increasing pervasiveness of AI in the real world, we seek to provide a focused venue for academic and industry researchers and practitioners to discuss research challenges and solutions associated with building AI systems under data scarcity and/or bias. In addition, authors can provide an optional two (2) page supplement at the end of their submitted paper (it needs to be in the same PDF file) focused on reproducibility. [Bests of ICDM], Zheng Zhang and Liang Zhao. Xiaojie Guo, Liang Zhao, Houman Homayoun, Sai Manoj Pudukotai Dinakarrao. To adapt SSL frameworks to build effective human-centric deep learning solutions for human-centric data, a number of key challenges and opportunities need to be explored. Topics include but not limited to: Large-scale and novel targeting technologies, Fraud, fairness, explainability and privacy, Intelligent assistants in job hunting and hiring automation, Large-scale and high performing data infrastructure, data analysis and tooling, Economics and causal inference in online jobs marketplace, Large-scale analytics of user behaviors in online jobs marketplace. As far as we know, we are the first workshop to focus on practical deep learning in the wild for AI, which is of great significance. Typically, we receive around 40~60 submissions to each previous workshop. This workshop on Trustworthy Autonomous Systems Engineering (TRASE) offers an opportunity to highlight state of the art research in trustworthy autonomous systems, as well as provide a vision for future foundational and applied advances in this critical area at the intersection of AI and Cyber-Physical Systems. Additional advantages are possible, including decreased computational resources to solve a problem, reduced time for the network to make predictions, reduced requirements for training set size, and avoiding catastrophic forgetting. Advances in complex engineering systems such as manufacturing and materials synthesis increasingly seek artificial intelligence/machine learning (AI/ML) solutions to enhance their design, development, and production processes. The PAKDD is one of the longest established and leading international conferences in the areas of data mining and knowledge discovery. Saliency-regularized Deep Multi-task Learning. Attendance is open to all. The aim of this workshop is to focus on both original research and review articles on various disciplines of ITS applications, including particularly AI techniques for ITS time-series data analyses, ITS spatio-temporal data analyses, advanced traffic management systems, advanced traveler information systems, commercial vehicle operation systems, advanced vehicle control and safety systems, advanced public transportation services, advanced information management services, etc. Papers will be submitted electronically using Easychair. TG-GAN: Continuous-time Temporal Graph Deep Generative Models with Time-Validity Constraints. 963-971, Apr-May 2015. The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2021), (acceptance rate: 23.6%), accepted. Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022), (Acceptance Rate: 15%), accepted. URL: https://sites.google.com/view/kdd22onlinemarketplaces Call For Papers (Submission deadline: June3, 2022) Identification of key challenges and opportunities for future research. Andy Doyle, Graham Katz, Kristen Summers, Chris Ackermann, Ilya Zavorin, Zunsik Lim, Sathappan Muthiah, Liang Zhao, Chang-Tien Lu, Patrick Butler, Rupinder Paul Khandpur. 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. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. Design, Automation and Test in Europe Conference (DATE 2020), long paper, (acceptance rate: 26%), accepted. Publication in HC-SSL does not prohibit authors from publishing their papers in archival venues such as NeurIPS/ICLR/ICML or IEEE/ACM Conferences and Journals. Full papers: Submissions must represent original material that has not appeared elsewhere for publication and that is not under review for another refereed publication. Zirui Xu, Fuxun Xu, Liang Zhao, and Xiang Chen. Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning. We will also have a panel discussion on the current and future of GNNs on both research and industry. The topics for AIBSD 2022 include, but are not limited to: This one-day workshop will include invited talks from keynote speakers, and oral/spotlight presentations of the accepted papers. Accepted papers will not be archived but will be hosted on the workshop website. We propose a full day workshop with the following sessions: The workshop solicits paper submissions from participants (26 pages). Position papers are welcome. How can we develop solid technical visions and new paradigms about AI Safety? We welcome the submissions in the following two formats: The submissions should adhere to theAAAI paper guidelines. [Call for papers] KDD 2022 Workshop on Decision Intelligence and Analytics for Online Marketplaces: Jobs, Ridesharing, Retail, and Beyond, CFP: IJCAI 2021 Reinforcement Learning for Intelligent Transportation Systems Workshop, Second Workshop on Marketplace Innovation. Furthermore, DNNs are data greedy in the context of supervised learning, and not well developed for limited label learning, for instance for semi-supervised learning, self-supervised learning, or unsupervised learning. Long talks (50 mins):Gabriel Peyr, (Mathematics, CNRS Senior Researcher);Yusu Wang, (Mathematics, Professor in CSE, UCSD);Caroline Uhler, (Statistics and CS, Associate Professor in EECS and IDSS, MIT); Short talks (25mins):Titouan Vayer, (Mathematics, Postdoctoral Researcher at ENS Lyon);Tam Le, (Computer Science, Research Scientist at RIKEN);Dixin Luo, (Computer Science, Assistant Professor in CS, Beijing Institute of Technology). Information-theoretic approaches provide a novel set of tools that can expand the scope of classical approaches to causal inference and discovery problems in a variety of applications. Yuyang Gao, Tanmoy Chowdhury (co-first author), Lingfei Wu, Liang Zhao. The financial services industry relies heavily on AI and Machine Learning solutions across all business functions and services. Please note that the KDD Cup workshop will haveno proceedingsand the authors retainfull rightsto submit or post the paper at any other venue. [paper] New self-supervised proxy tasks or new approaches using self-supervised models in speech and audio processing. SIGKDD Explorations, Vol. In addition to that, we propose a shared task on one of the challenging SDU tasks, i.e., acronym extraction and disambiguation in multiple languages text. Yuanqi Du, Xiaojie Guo, Yinkai Wang, Amarda Shehu, Liang Zhao. Online . ", ACM Transactions on Spatial Algorithms and Systems (TSAS), (Acceptance Rate: 11%), Volume 2 Issue 4, Acticle No. Interpreting and Evaluating Neural Network Robustness. What safety engineering considerations are required to develop safe human-machine interaction? arXiv preprint arXiv:2207.09542 (2022). Recent years have witnessed growing interest in human and AI systems with the increasing realisation that machines can indeed meet objectives specified but the real question becomes have they been given the right objectives. With the rapid development of advanced techniques on the intersection between information theory and machine learning, such as neural network-based or matrix-based mutual information estimator, tighter generalization bounds by information theory, deep generative models and causal representation learning, information theoretic methods can provide new perspectives and methods to deep learning on the central issues of generalization, robustness, explainability, and offer new solutions to different deep learning related AI applications.This workshop aims to bring together both academic researchers and industrial practitioners to share visions on the intersection between information theory and deep learning, and their practical usages in different AI applications. We solicit papers describing significant and innovative research and applications to the field of job marketplaces. NOTE: Mandatory abstract deadline: 2022-08-08 Deadline: AAAI 157. These submissions would benefit from additional exposure and discussion that can shape a better future publication. Authors are invited to send a contribution in the AAAI-22 proceedings format. Xiaojie Guo, Liang Zhao, Zhao Qin, Lingfei Wu, Amarda Shehu, and Yanfang Ye. Xuchao Zhang, Shuo Lei, Liang Zhao, Arnold Boedihardjo, Chang-Tien Lu, "Robust Regression via Heuristic Corruption Thresholding and Its Adaptive Estimation Variation", ACM Transactions on Knowledge Discovery from Data (TKDD), (impact factor: 1.98), accepted, 2019. How do metrics of capability and generality, and the trade-offs with performance affect safety? 2022. We will include a panel discussion to close the workshop, in which the audience can ask follow up questions and to identify the key AI challenges to push the frontiers in Chemistry. What is the status of existing approaches in ensuring AI and Machine Learning (ML) safety, and what are the gaps? Please keep your paper format according to AAAI Formatting Instructions (two-column format). 2022. Public health authorities and researchers collect data from many sources and analyze these data together to estimate the incidence and prevalence of different health conditions, as well as related risk factors. BERT and GPT in NLP and SimCLR and BYOL in CV are famous examples in this direction. If these formalities are not completed in time, you will have to file a new application at a later date. Novel mechanisms for eliciting and consuming user feedback, recommender, structured and generative models, concept acquisition, data processing, optimization; HCI and visualization challenges; Analysis of human factors/cognition and user modelling; Design, testing and assessment of IML systems; Studies on risks of interaction mechanisms, e.g., information leakage and bias; Business use cases and applications. The bottleneck to discovery is now our ability to analyze and make sense of heterogeneous, noisy, streaming, and often massive datasets. We expect 50~75 participants and potentially more according to our past experiences. ISBN: 978-981-16-6053-5. The academic session will focus on most recent research developments on GNNs in various application domains. SDU is expected to host 50-60 attendees. Submissions must be formatted in the AAAI submission format (https://www.aaai.org/Publications/Templates/AuthorKit22.zip) All submissions should be done electronically via EasyChair. The final schedule will be available in November. 2022. However, you may visit "Cookie Settings" to provide a controlled consent. The aim of the hack-a-thon is not only to foster innovation and potentially provide answers to outstanding research problems, but rather to engage the community and create new collaborations. Submissions are limited to a total of 5 pages for initial submission (up to 6 pages for final camera-ready submission), excluding references or supplementary materials, and authors should only rely on the supplementary material to include minor details that do not fit in the 5 pages. Apr 25th through Fri the 29th, 2022. . 2022. This cookie is set by GDPR Cookie Consent plugin. Integration of probabilistic inference in training deep models. The program consists of poster sessions for accepted papers, and invited and spotlight talks. We will specifically invite participants of the DSTC10 tasks, track organizers, and authors of accepted papers in the general technical track. The eligibility criteria for attending the workshop will be registration in the conference/workshop as per AAAI norms. The workshop is being organized by application area or other, panels, invited speakers, interactive, small groups, discussions, presentations. The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022) (Acceptance Rate: 14.99%), accepted, 2022. Submission site:https://cmt3.research.microsoft.com/ITCI2022, Murat Kocaoglu, Chair (Purdue University, mkocaoglu@purdue.edu), Negar Kiyavash (EPFL, negar.kiyavash@epfl.ch), Todd Coleman (UCSD, tpcoleman@ucsd.edu), Supplemental workshop site:https://sites.google.com/view/itci22. Oral presentations: 10 minute presentation for oral papers. The 9th International Conference on Learning Representations (ICLR 2021), (acceptance rate: 28.7%), accepted. Data Mining and Knowledge Discovery (DMKD), (impact factor: 3.670), accepted. However, we will also accept anonymous submissions. KDD 2022 : 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Conference Series : Knowledge Discovery and Data Mining Link: https://kdd.org/kdd2022/ Call For Papers [Empty] Related Resources KDD 2023 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING Self-Paced Robust Learning for Leveraging Clean Labels in Noisy Data. Zhiqian Chen, Lei Zhang, Gaurav Kolhe, Hadi Mardani Kamali, Setareh Rafatirad, Sai Manoj Pudukotai Dinakarrao, Houman Homayoun, Chang-Tien Lu, Liang Zhao. Liang Zhao, Junxiang Wang, and Xiaojie Guo. We invite submissions to the AAAI-22 workshop on Graphs and more Complex structures for Learning and Reasoning to be held virtually on February 28 or March 1, 2022. It will include multiple keynote speakers, invited talks, a panel discussion, and two poster sessions for the accepted papers. 1923-1935, 1 Oct. 2020, doi: 10.1109/TKDE.2019.2912187. Submit to:https://cmt3.research.microsoft.com/AIBSD2022, Kuan-Chuan Peng (Mitsubishi Electric Research Laboratories, kp388@cornell.edu), Ziyan Wu (UII America, Inc., wuzy.buaa@gmail.com), Supplemental workshop site:https://aibsdworkshop.github.io/2022/index.html. : Papers must be in PDF format, and formatted according to the new Standard ACM Conference Proceedings Template. Knowledge Discovery and Data Mining is an interdisciplinary area focusing Papers can be submitted here as an extended abstract (4 pages limit excluding references) or a short paper (6 pages limit excluding references). Computer Science and Engineering, INESC-ID, IST Ulisboa, Lisbon, Portugal currently at Sorbonne University, Paris, France silvia.tulli@gaips.inesc-id.pt), Prashan Madumal (Science and Information Systems, University of Melbourne, Parkville, Australia pmathugama@student.unimelb.edu.au), Mark T. Keane (School of Computer Science, University College Dublin, Dublin, Ireland mark.keane@ucd.ie), David W. Aha (Navy Center for Applied Research in AI, Naval Research Laboratory, Washington, DC, USA david.aha@nrl.navy.mil), Adam Johns (Drexel University, Philadelphia, PA USA), Tathagata Chakraborti (IBM Research AI, Cambridge, MA USA), Kim Baraka (VU University Amsterdam, Netherlands), Isaac Lage (Harvard University, Cambridge, MA USA), David Martens (University of Antwerp, Belgium), Mohamed Chetouani (Sorbonne Universit, Paris, France), Peter Flach (University of Bristol, United Kingdom), Kacper Sokol (University of Bristol, United Kingdom), Ofra Amir (Technion, Haifa, Israel), Dimitrios Letsios (Kings College London, London, United Kingdom), Supplemental workshop site:https://sites.google.com/view/eaai-ws-2022/topic. Deep Spatial Domain Generalization. However, workshop organizers may set up any archived publication mechanism that best suits their workshop. Spatio-temporal Event Forecasting Using Incremental Multi-source Feature Learning. Knowledge representation for business documents. Full papers are allocated 20m presentation and 10m discussion. Adversarial attacking deep learning systems, Robust architectures against adversarial attacks, Hardware implementation and on-device deployment, Benchmark for evaluating model robustness, New methodologies and architectures for efficient and robust deep learning, December 3, 2021 Acceptance Notification, Applications of privacy-preserving AI systems, Differential privacy: theory and applications, Distributed privacy-preserving algorithms, Privacy preserving optimization and machine learning, Privacy preserving test cases and benchmarks. Full (8 pages) and short (4 pages, work in progress) papers, AAAI style. to protect data owner privacy in FL. AAAI is pleased to present the AAAI-22 Workshop Program. Extracting knowledge or insights from this abundance of data lies at the heart of 21st century discovery, which can be used to inform decisions, coordinate activities, optimize processes, improve products and services, as well as enhance productivity and innovation across a wide range of business and scientific problems. To view them in conference website timezones, click on them. Please refer and submit through theLearning Network Architecture During Trainingworkshop website, which has more detailed information. 4. For example: The workshop will be a 1-day event with a number of invited talks by prominent researchers, a panel discussion, and a combination of oral and poster presentations of accepted papers. The following paper categories are welcome: Submission site:https://sites.google.com/view/eaai-ws-2022/call, Silvia Tulli (Dept. 689-698, Barcelona, Spain, Dec 2016. The reproducibility papers include a clarification phase: Deadlines refer to 23:59 (11:59pm) in the AoE (Anywhere on Earth) time zone. Summer. Such advances would enrich the range of applicability of semi-autonomous systems to real-world tasks, most of which involve cooperation with one or more human partners. However, despite increasing interest from various subfields, AI/ML techniques are yet to fulfill their full promise in achieving these advances. Long Beach, California, USA . After the submission deadline, the names and order of authors cannot be changed. Submissions should be formatted using the AAAI-2022 Author Kit. Submission site:https://openreview.net/group?id=AAAI.org/2022/Workshop/AIAFS, Girish Chowdhary (University of Illinois, Urbana Champaign), Baskar Ganapathysubramanian (Iowa State University; contact: baskarg@iastate.edu), George Kantor (Carnegie Mellon University), Soumyashree Kar (Iowa State University), Koushik Nagasubramanian (Iowa State University), Soumik Sarkar (Iowa State University), Katia Sycara (Carnegie Mellon University), Sierra Young (North Carolina State University), Alina Zare (University of Florida, Gainesville), Supplemental workshop site:https://aiafs-aaai2022.github.io/. Time Series Clustering in Linear Time Complexity. All accepted papers will be archived on the workshop website, but there will not be formal proceedings. This website uses cookies to improve your experience while you navigate through the website. Recently developed tools and cutting-edge methodologies coming from the theory of optimal transport have proved to be particularly successful for these tasks. Like other systems, ML systems must meet quality requirements. Some will be selected for spotlight talks, and some for the poster session. The workshop organizers invite paper submissions on the following (and related) topics: This workshop will be a one-day workshop, featuring invited speakers, poster presentations, and short oral presentations of selected accepted papers. Encore track papers that have been recently published, or accepted for publication in a conference or journal. The AAAI-22 workshop program includes 39 workshops covering a wide range of topics in artificial intelligence. This workshop will encourage researchers from interdisciplinary domains working on multi-modality and/or fact-checking to come together and work on multimodal (images, memes, videos etc.) Important Dates. Semantic understanding of business documents. the 33rd Annual Computer Security Applications Conference (ACSAC 2018), (acceptance rate: 20.1%), San Juan, Puerto Rico, USA, Dec 2018, accepted. Zheng Chai, Yujing Chen, Ali Anwar, Liang Zhao, Yue Cheng, Huzefa Rangwala. [Best Paper Candidate], Minxing Zhang, Dazhou Yu, Yun Li, Liang Zhao. The workshop is a full day. https://doi.org/10.1007/s10707-019-00376-9. 1, 2022: Call For Paper: The Undergraduate Consortium at SIGKDD 2022 is available at, Mar. Maria Malik, Hassan Ghasemzadeh, Tinoosh Mohsenin, Rosario Cammarota, Liang Zhao, Avesta Sasan, Houman Homayoun, Setareh Rafatirad. It further combines academia and industry in a quest for well-founded practical solutions. Deadline in . ADMM for Efficient Deep Learning with Global Convergence. applications: ridesharing, online retail, food delivery, house rental, real estate, and more. It is expected that one of the authors of accepted contributions will register and attend the workshop to present the work in video in-person in the workshops Paper Sessions. SIAM International Conference on Data Mining (SDM 2023) (Acceptance Rate: 27.4%), accepted. After seventh highly successful events, the eighth Symposium on Visualization in Data Science (VDS) will be held at a new venue, ACM KDD 2022 as well as IEEE VIS 2022. What are the primary lessons learned from the model failures? The Conference. Fang Jin, Wei Wang, Liang Zhao, Edward Dougherty, Yang Cao, Chang-Tien Lu, and Naren Ramakrishnan. Any participant who experiences unacceptable behavior may contact any current member of the SIGMOD Executive Committee, the PODS Executive Committee, DBCares, or this year's D&I co-chairs Pnar Tzn (pito@itu.dk) and Renata Borovica-Gajic (renata.borovica@unimelb.edu.au). Analytical cookies are used to understand how visitors interact with the website. in Proceedings of the IEEE International Conference on Data Mining (ICDM 2015), regular paper (acceptance rate: 8.4%), Atlantic City, NJ, pp. Expected attendance is 40-50 people. AI is one of these transformative technologies that is now achieving great successes in various real-world applications and making our life more convenient and safer. This calls for novel methods and new methodologies and tools to address quality and reliability challenges of ML systems. The cookie is used to store the user consent for the cookies in the category "Performance". Track 1 covers the issues and algorithms pertinent to general online marketplaces as well as specific problems and applications arising from those diverse domains, such as ridesharing, online retail, food delivery, house rental, real estate, and more. Small Molecule Generation via Disentangled Representation Learning. anomaly detection, and ensemble learning. Fine tuning a neural network is very time consuming and far from optimal. This workshop aims to bring together FL researchers and practitioners to address the additional security and privacy threats and challenges in FL to make its mass adoption and widespread acceptance in the community. There is a need for the research community to develop novel solutions for these practical issues. Workshops will be held Monday and Tuesday, February 28 and March 1, 2022. What AI safety considerations and experiences are relevant from industry? Our topics of interest span over prediction, planning, and decision problems for online marketplaces, including but not limited to. These challenges and issues call for robust artificial intelligence (AI) algorithms and systems to help. ACM Transactions on Knowledge Discovery from Data (TKDD), (impact factor: 3.089), accepted. "Multi-Task Learning for Spatio-Temporal Event Forecasting." Submissions can be original research contributions, or abstracts of papers previously submitted to top-tier venues, but not currently under review in other venues and not yet published. The growing popularity of NAS methods demonstrates the communitys hunger for better ways of choosing or evolving network architectures that are well-matched to the problem at hand.