Liang Zhao, Amir Alipour-Fanid, Martin Slawski and Kai Zeng. Question answering on business documents. search, ranking, recommendation, and personalization. Big data Journal (impact factor: 1.489), vo. "Automatic Targeted-Domain Spatiotemporal Event Detection in Twitter." Sign-regularized multi-task learning. Deep Graph Translation. arXiv preprint arXiv:2212.03954 (2022). Deep learning and statistical methods for data mining. We aim to bring together researchers in AI, healthcare, medicine, NLP, social science, etc. IEEE Transactions on Information Forensics and Security (TIFS), (impact factor: 7.178), accepted. Distributed Self-Paced Learning in Alternating Direction Method of Multipliers. We expect ~60 attendees. What is the status of existing approaches in ensuring AI and Machine Learning (ML) safety, and what are the gaps? Visualization is an integral part of data science, and essential to enable sophisticated analysis of data. The KDD 2022 program promises to be the most robust and diverse to date, with keynote presentations, industry-led sessions, workshops, and tutorials spanning a wide range of topics - from data-driven humanitarian mapping and applied data science in healthcare to the uses of artificial intelligence (AI) for climate mitigation and decision . Frontiers in Neurorobotics, (impact factor: 2.574), accepted. Yevgeniy Vorobeychik (Washington University in St. Louis), Bruno Sinopoli (Washington University in St. Louis), Jinghan Yang (Washington University in St. Louis), Bo Li (UIUC), Atul Prakash (University of Michigan), Supplemental Workshop site:https://jinghany.github.io/trase2022/. Hence, there is a need for research and practical solutions to ML security problems.With these in mind, this workshop solicits original contributions addressing problems and solutions related to dependability, quality assurance and security of ML systems. Yiming Zhang, Yujie Fan, Yanfang Ye, Liang Zhao, Jiabin Wang, and Qi Xiong. Poster/short/position papers submission deadline: Nov 5, 2021Full paper submission deadline: Nov 5, 2021Paper notification: Dec 3, 2021. How to Write and Publish Research Papers for the Premier Forums in Knowledge & Data Engineering: Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018), Oral presentation (acceptance rate: 11.0%), New Orleans, US, Feb 2018, pp. For instance, advanced driver assistance systems and autonomous cars have been developed based on AI techniques to perform forward collision warning, blind spot monitoring, lane departure warning systems, traffic sign recognition, traffic safety, infrastructure management and congestion, and so on. Despite the great success of deep neural networks (DNNs) in many artificial intelligence (AI) tasks, they still suffer from limitations, such as poor generalization behavior for out-of-distribution (OOD) data, vulnerability to adversarial examples, and the black-box nature of DNNs. Hence, AI methods are required to understand and protect the cyber domain. Identification of information-theoretic quantities relevant for causal inference and discovery. We invite submission of papers describing innovative research on all aspects of knowledge discovery and data science, ranging from theoretical foundations to novel models and algorithms for data science problems in science, business, medicine, and engineering. Apr 25th through Fri the 29th, 2022. . The IEEE International Conference on Data Mining (ICDM 2022), full paper, (Acceptance Rate: 9.77%), to appear, 2022. Deep Graph Transformation for Attributed, Directed, and Signed Networks. As for the Kraken, they made one trade a month ago to acquire a seventh defenceman, Jaycob Megna and did nothing else (from 'Kraken remain quiet as NHL trade deadline passes,' The Seattle . Liang Zhao, Ting Hua, Chang-Tien Lu, and Ing-Ray Chen. To push forward the research on acronym understanding in scientific text, we propose two shared tasks on acronym extraction (i.e., recognizing acronyms and phrases in text) and disambiguation (i.e., finding the correct expansion for an ambiguous acronym). In Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2020), (acceptance rate: 16.8%), August 23-27, 2020, Virtual Event, CA, USA. This policy also applies to papers that overlap substantially in technical content with papers previously published, accepted, or under review. Liang Zhao, Feng Chen, and Yanfang Ye. 1, Sec. It has profoundly impacted several areas, including computer vision, natural language processing, and transportation. However, workshop organizers may set up any archived publication mechanism that best suits their workshop. 639-648, Nov 2015. International Journal of Digital Earth, (impact factor: 3.097), 25 Aug 2020, https://doi.org/10.1080/17538947.2020.1809723. We accept two types of submissions full research papers no longer than 8 pages (including references) and short/poster papers with 2-4 pages. A 2-day workshop to share knowledge and research on five tracks of DSTC-10 and general related technical track. Continuous refinement of AI models using active/online learning. KDD 2022 is a dual-track conference that provides distinct programming in research and applied data science. We will receive the paper on the CMT system. Following this AAAI conference submission policy, reviews are double-blind, and author names and affiliations should NOT be listed. Spatial Event Forecasting in Social Media with Geographically Hierarchical Regularization. All papers must be submitted in PDF format, using the AAAI-22 author kit. Transformations in many fields are enabled by rapid advances in our ability to acquire and generate data. These models can also generate instant feedback to instructors and help them to improve their teaching effectiveness. Modeling Health Stage Development of Patients with Dynamic Attributed Graphs in Online Health Communities. These lead to security considerations: (1) securing personal health information, genetic material, intellectual property, and digital health records, (2) balancing privacy rights and data ownership concerns in solutions using network and mobile data, (3) defending AI for biology use cases to deter automated attacks at scale. California, United Stes. Hence, this workshop will focus on introducing research progress on applying AI to education and discussing recent advances of handling challenges encountered in AI educational practice. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '22), 2022. By the end of this century, the earths population is projected to increase by 45% with available arable land decreasing by 20% coupled with changes in what crops these arable lands can best support; this creates the urgent need to enhance agricultural productivity by 70% before 2050. The workshop also welcomes participants of SUPERB and Zero Speech challenge to submit their results. In Proceedings of the 20th International Conference on Data Mining (ICDM 2020), (acceptance rate: 9.8%), November 17-20, 2020, Virtual Event, Sorrento, Italy, 10 pages. Participants are welcomed to submit their system reports to be presented in the workshop. To provide proper alerts and timely response, public health officials and researchers systematically gather news and other reports about suspected disease outbreaks, bioterrorism, and other events of potential international public health concern, from a wide range of formal and informal sources. 2022. Short or position papers of up to 4 pages are also welcome. Finally, the workshop will welcome papers that describe the release of privacy-preserving benchmarks and data sets that can be used by the community to solve fundamental problems of interest, including in machine learning and optimization for health systems and urban networks, to mention but a few examples. It is anticipated that this will be an in-person workshop, subject to changing travel restrictions and health measures. Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Lingfei Wu, Charu Aggarwal, and Chang-Tien Lu. of London). At the same time, multimodal hate-speech detection is an important problem but has not received much attention. Liang Zhao, Jiangzhuo Chen, Feng Chen, Fang Jin, Wei Wang, Chang-Tien Lu, and Naren Ramakrishnan. At least one author of each accepted submission must be present at the workshop. 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. In recent years, various information theoretic principles have also been applied to different deep learning related AI applications in fruitful and unorthodox ways. Deep Learning models are at the core of research in Artificial Intelligence research today. These research trends inform the need to explore the intersection of AI with behavioral science and causal inference, and how they can come together for applications in the social and health sciences. All time are 23:59, AoE (Anywhere on Earth), Hongteng Xu (Renmin University of China, hongtengxu@ruc.edu.cn, main contact), Julie Delon (Universit de Paris, julie.delon@u-paris.fr), Facundo Mmoli (Ohio State University, facundo.memoli@gmail.com), Tom Needham (Florida State University, tneedham@fsu.edu). 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. We cordially welcome researchers, practitioners, and students from academia and industry who are interested in understanding and discussing how data scarcity and bias can be addressed in AI to participate. For general inquiries about AI2ASE, please write to the lead organizer aryan.deshwal@wsu.edu or jana.doppa@wsu.edu. San Francisco, USA . Realizing the vision of Document Intelligence remains a research challenge that requires a multi-disciplinary perspective spanning not only natural language processing and understanding, but also computer vision, layout understanding, knowledge representation and reasoning, data mining, knowledge discovery, information retrieval, and more all of which have been profoundly impacted and advanced by deep learning in the last few years. Liang Zhao, Qian Sun, Jieping Ye, Feng Chen, Chang-Tien Lu, and Naren Ramakrishnan. Deep Generative Model for Periodic Graphs. Generative Deep Learning for Macromolecular Structure and Dynamics, Current Opinion in Structural Biology, (impact factor: 7.108), Section on Theory and Simulation/Computational Methods 67: 170-177, 2021 accepted. 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. "Key Player Identification in Underground Forums over Attributed Heterogeneous Information Network Embedding Framework",The 28th ACM International Conference on Information and Knowledge Management (CIKM 2019), long paper, (acceptance rate: 19.4%), Beijing, China, accepted. Qingzhe Li, Liang Zhao, Jessica Lin and Yi-ching Lee. Submissions introducing interesting experimental phenomena and open problems of optimal transport and structured data modeling are welcome as well. The accepted papers will be posted on the workshop website and will not appear in the AAAI proceedings. Optimal transport theory, including statistical and geometric aspects; Gromov-Wasserstein distance and its variants; Bayesian inference for/with optimal transport; Gromovization of machine learning methods; Optimal transport-based generative modeling. The post-launch session includes the invited talks, shared task winners presentations, and a panel discussion on the resources, findings, and upcoming challenges. The topics of interest include but are not limited to: Theoretical and Computational Optimal Transport: Optimal Transport-Driven Machine Learning: Optimal Transport-Based Structured Data Modeling: The full-day workshop will start with two long talks and one short talk in the morning. 4701-4707, San Francisco, California, USA, Feb 2017. The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2021), (acceptance rate: 23.6%), accepted. Given the ever-increasing role of the World Wide Web as a source of information in many domains including healthcare, accessing, managing, and analyzing its content has brought new opportunities and challenges. ML4OR will serve as an interdisciplinary forum for researchers in both fields to discuss technical issues at this interface and present ML approaches that apply to basic OR building blocks (e.g., integer programming solvers) or specific applications. 3434-3440, Melbourne, Australia, Aug 2017. This is a 1-day workshop involving talks by pioneer researchers from respective areas, poster presentations, and short talks of accepted papers. Dynamic Tracking and Relative Ranking of Airport Threats from News and Social Media. However, despite increasing interest from various subfields, AI/ML techniques are yet to fulfill their full promise in achieving these advances. Factorized Deep Generative Models for End-to-End Trajectory Generation with Spatiotemporal Validity Constraints. Negar Etemadyrad, Qingzhe Li, Liang Zhao. Jinliang Ding, Liang Zhao, Changxin Liu, and Tianyou Chai. ReForm: Static and Dynamic Resource-Aware DNN Reconfiguration Framework for Mobile Devices. Causal inference is one of the main areas of focus in artificial intelligence (AI) and machine learning (ML) communities. This workshop seeks to explore new ideas on AI safety with particular focus on addressing the following questions: Contributions are sought in (but are not limited to) the following topics: To deliver a truly memorable event, we will follow a highly interactive format that will include invited talks and thematic sessions. The full-day workshop will start with an opening remark followed by long research paper presentations in the morning. The goal of this workshop is to bring together the causal inference, artificial intelligence, and behavior science communities, gathering insights from each of these fields to facilitate collaboration and adaptation of theoretical and domain-specific knowledge amongst them. Novel AI-based techniques to improve modeling of engineering systems. However, these real-world applications typically translate to problem domains where it is extremely challenging to even obtain raw data, let alone annotated data. The submissions must be in PDF format, written in English, and formatted according to the AAAI camera-ready style. Supplemental Workshop site:https://rl4ed.org/aaai2022/index.html. The goal of ITCI22 is to bring together researchers working at the intersection of information theory, causal inference and machine learning in order to foster new collaborations and provide a venue to brainstorm new ideas, exemplify to the information theory community causal inference and discovery as an application area and highlight important technical challenges motivated by practical ML problems, draw the attention of the wider machine learning community to the problems at the intersection of causal inference and information theory, and demonstrate to the community the utility of information-theoretic tools to tackle causal ML problems. Our topics of interest span over prediction, planning, and decision problems for online marketplaces, including but not limited to. Pourya Hoseinip, Liang Zhao, and Amarda Shehu. FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers. [Best Poster Runner-Up Award]. [Best Paper Award]. . Government day with NSF, NIH, DARPA, NIST, and IARPA, Local industries in the DC Metro Area, including the Amazons second headquarter, New initiatives at KDD 2022: undergraduate research and poster session, Early career research day with postdoctoral scholars and assistant professors in a mentoring workshop and panel, Workshops and hands-on tutorials on emerging topics. Interpretable Molecular Graph Generation via Monotonic Constraints. ACM, New York, NY, USA, 10 pages. Programming Languages, Domain specific languages, Libraries and software tools for integration of various learning and reasoning paradigms. convolutional neural network (CNN), recurrent neural network (RNN), etc.) The 30th International World Wide Web Conference, the Web Conference (WWW 2021), (acceptance rate: 20.6%), accepted. Novel ML-accelerated optimization for conceptual/detailed system design. Submissions should be formatted using the AAAI-2022 Author Kit. Different from machine learning, Knowledge Discovery and Data Mining (KDD) is Videos have become an omnipresent source of knowledge: courses, presentations, conferences, documentaries, live streams, meeting recordings, vlogs. CoRL 2023 97 days 17h 29m 15s November 06-09, 2023. 5, pp. Molecules, (impact factor: 4.411), accepted. NOTE: Mandatory abstract deadline: 2022-08-08 Deadline: AAAI 157. All deadlines are at 11:59 PM anytime in the world. in Proceedings of the 22st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2016), applied data science track, accepted (acceptance rate: 19.9%), pp. Proceedings of the ACM on Human-Computer Interaction (CSCW 2022), to appear, 2022. "The EMBERS architecture for streaming predictive analytics." Integration of Deep Learning and Relational Learning. have been popularly applied into image recognition and time-series inferences for intelligent transportation systems (ITS). The deadline for the submissions is July 31st, 2022 11.59 PM (Anywhere on Earth time). Deep Graph Spectral Evolution Networks for Graph Topological Evolution. SUPERB is a benchmarking platform that allows the community to train, evaluate, and compare the speech representations on diverse downstream speech processing tasks. Naren Ramakrishnan, Patrick Butler, Sathappan Muthiah, Nathan Self, Rupinder Khandpur, Parang Saraf, Wei Wang, Jose Cadena, Anil Vullikanti, Gizem Korkmaz, Chris Kuhlman, Achla Marathe, Liang Zhao, Ting Hua, Feng Chen, et al.. "'Beating the news' with EMBERS:forecasting civil unrest using open source indicators." We send a public call and we assume the workshop will be of interest to many AAAI main conference audiences; we expect 50 participants.