Prof. Yongfeng Zhang receives NSF CAREER Award

Congratulations to Prof. Yongfeng Zhang for receiving the Faculty Early Career Development (CAREER) Award from the National Science Foundation (NSF) for his project titled "CAREER: Towards Conversational Recommendation Systems: Explainability, Fairness, and Human-in-the-Loop Learning". The award is from October 2021 to September 2026 with the total awarded amount $550,000. The Faculty Early Career Development (CAREER) Program is an NSF foundation-wide activity that offers the National Science Foundation's most prestigious awards in support of early-career faculty who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization. The project aims to develop explainable, fairness-aware, trustworthy and responsible AI systems. Recent advances in Artificial Intelligence AI have accumulated a rich toolbox of models for information retrieval, natural language processing and personalized recommendation. By optimizing over benchmark datasets, many of the models were developed with an algorithmic consideration instead of putting human at the central consideration. However, the ultimate goal of AI is to serve humans, collaborate with humans, and, ultimately, benefit humans. As a result, algorithmic approaches to AI must put humans in the loop for model design, implementation and validation. This project focuses on conversational AI, a promising approach towards putting humans in the loop, which enables direct conversation between human and AI for model learning. In particular, the project explores conversational recommender systems to help users in information seeking and decision making. It will develop explainable and fairness-aware algorithms for conversational recommendation. Presentation of the work and demos will help to engage with wider audiences that are interested in computational research. By integrating transparency and fairness principles into computer science courses on areas such as Information Retrieval, Data Mining and Artificial Intelligence, results from the project will educate students to understand how AI can be not only useful but also socially responsible. This project will develop a general framework for conversational recommendation that bridges natural language understanding and dialog state management. With the framework, the project will explore three directions. The first direction aims at developing explainable conversation strategies based on human-machine collaborative reasoning, which brings cognitive ease to users and helps to build trust between human and AI. The second direction explores fairness-aware conversation strategies based on short-term and long-term fairness learning, which helps to achieve fair recommendation experiences between advantages and disadvantaged users. The third direction aims at developing a learning to evaluate protocol for conversational recommendation, which unifies the advantages of online crowd-sourcing and offline model learning for evaluation. The project will also develop a prototype conversational recommendation platform as a class project to support the education of responsible AI. The project will result in the dissemination of shared data and evaluation platforms to the Information Retrieval, Data Mining, Recommender System, and broader AI communities. More information about the project can be found on the NSF webpage:

Prof. Yongfeng Zhang receives Facebook Faculty Research Award

Congratulations to Prof. Yongfeng Zhang for receiving the Facebook Faculty Research Award for his project titled "Towards a Sustainable Social Platform based on Explainable and Fairness-aware Recommendation" with an awarded amount $75,000. Social platforms are three-sided marketplaces, including the users, the content producers, and the platform. The content producers produce various types of items to be broadcasted in the system, including but not limited to text messages, articles, images, video clips, and advertisements. Users interact with these items and interact with other users for information seeking, entertainment, and productivity. Meanwhile, the platform serves as the essential tool to connect the users and their interested items. One of the most fundamental approaches to connecting users with the appropriate items is through personalization and recommendation, which aims to learn the personalized preferences of the users through advanced machine learning techniques so as to understand their information needs and connect the users with the best items. However, most of the existing methods for personalized recommendation are designed based on short-term optimization considerations, but do not put the platform's long-term sustainable development into consideration. For example, matching-based or sequence-based recommendation models are optimized over users' previously clicked items so as to predict their future actions for recommendation. This purely click-driven optimization design makes the algorithms vulnerable to several important risks such as unfair resource allocations, feedback-loops and echo chambers, as well as unexplainable algorithimc decisions. These problems weakens the platform's sustainable development over each of the three stakeholders: 1) Unfair chances of exposure results in loss of content producers, 2) feedback loops and echo chambers result in narrowed user interests, 3) lack of explainability and trustworthiness results in scarified conversion rate and profit of the platform. This project explores explainable and fairness-aware techniques to address the above problems, including Long-term Fairness for Sustainable Recommendation, Causal debias for mitigating feedback loops and echo chambers, and Counterfactual explainable recommendations. Algorithms and insights developed from this project will be integrated into the Facebook recommendaiton system and thus benefit billions of users.  

Ryder, Barbara

Best Paper Award to Prof. Desheng Zhang

Congratulations to Prof. Desheng Zhang on being recognized with the Best Paper Award of ACM/IEEE 12th International Conference on Cyber-Physical Systems (ICCPS 2021) for his coauthored paper "DeResolver: a decentralized negotiation and conflict resolution framework for smart city services"! ACM/IEEE ICCPS is the premier single-track conference for advances in Cyber-Physical Systems (CPS), including theory, tools, applications, systems, testbeds, and field deployments, focusing on the development of fundamental principles that underpin the integration of cyber and physical elements. This year, ICCPS accepted 20 papers out of 77 submissions and only the DeResolver paper was recognized with the Best Paper Award. This paper is part of a large NSF Smart City project where Prof. Desheng Zhang is the Lead PI to address the fundamental challenge of large-scale systems-of-systems with applications to Smart City Service Conflicts. This paper provided an important contribution to this direction, combining theoretical guarantees with machine learning optimization as commented by the TPC of ICCPS 21. The detail of the paper is given here

Prof. Desheng Zhang receives NSF CAREER Award

Congratulations to Prof. Desheng Zhang for receiving the Faculty Early Career Development (CAREER) Award from the National Science Foundation (NSF) for his project titled "CAREER: Human Mobility Prediction and Intervention based on Cross-Domain Infrastructure-Human Interactions". The award is from Jan 2022 to Dec 2026 and the total budget is $500,000. The CAREER Program is an NSF-wide activity that offers the National Science Foundation's most prestigious awards in support of early-career faculty, who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization. This project aims to model and support human mobility in real time at an urban scale. Better models of human mobility can help meet both sustainability challenges (through predicting traffic congestion, air quality, and energy consumption) and improve urban resilience to disruptive events (such as infrastructure failures, natural disasters, or pandemics). The key idea of the project is that people's increasingly frequent interaction with transportation, communication, financial, and other infrastructure can be used to understand mobility patterns. However, collecting and integrating this information into mobility models is still an open challenge. Further, people's collective decisions can negatively impact infrastructure, increasing wait times and reducing capacity in both transit and information infrastructures. Through collecting and integrating mobility-related behavior across multiple sources, the project team will advance the state of the art around mobility modeling methods and develop interventions that encourage people to make choices that improve mobility outcomes at scale, especially during crisis events. The team will also develop educational materials to train students to be both future researchers and workers who possess data collection and modeling expertise, particularly around questions of human mobility. The project is structured as two main thrusts that align with the goals of mobility modeling and mobility interventions. The first thrust for mobility prediction will explore the correlation and interdependency of interactions across multiple types of infrastructure, notably transportation, communication, and financial interactions. This will be done through advancing techniques based on multi-view learning to integrate cross-domain interactions, which will be integrated into a prediction framework using a correlation-driven multi-task recurrent neural network architecture. The second thrust aims to improve urban resilience by developing interventions to improve mobility under disruptive events. The team will use a novel dynamic Markov decision process formulation solved with distributed deep reinforcement learning to develop recommendations that enhance collective mobility, such as new departure times or routes for individuals, or road closures and transit capacity allocations for city planners. These models will leverage and be evaluated using existing datasets of infrastructure interaction and disrupted mobility collected before, during, and after the COVID-19 pandemic. Together, this work will lead to general principles, design methodologies, and a long-term research trajectory for cross-domain infrastructure-human interaction. More information about the award can be found from the NSF website:

Zhang, Qiong

Dr. Zhang is an Assistant Professor in the Psychology Department, and is also affiliated with the Department of Computer Science and the Rutgers Center for Cognitive Science. Dr. Zhang received her Ph.D. in 2019 from Carnegie Mellon University jointly in the Machine Learning Department under the School of Computer Science, and the Center for the Neural Basis of Cognition. She completed additional postdoctoral training in the Princeton Neuroscience Institute.   Her research combines computational modeling, behavioral methods and neural imaging to understand human memory. She is interested in how the human memory system optimally encodes and retrieves information, and how we as researchers can design methods to improve human memory performance.

Professors Wang and Zhang receive NSF RI grant

Congratulations to Profs. Hao Wang and Yongfeng Zhang, who have received an NSF RI Small Grant for their project titled "Enabling Interpretable AI via Bayesian Deep Learning", for an amount of $499,926, covering a three-year period starting from 10/1/2021. Interpretability is one of the fundamental obstacles on the adoption and deployment of deep-learning-based AI systems across various fields such as healthcare, e-commerce, transportation, earth science, and manufacturing. An ideal interpretable model should be able to interpret its prediction using human-understandable concepts, conform to conditional dependencies in the real world, and handle uncertainty in data (e.g., how certain the model is about the rainfall tomorrow). The goal of this project is to develop a general interpreter framework for deep learning models to natively support these desiderata. Methods developed in this project will be applied in health monitoring to interpret models’ reasoning on patient status, and in recommender systems to interpret models’ recommended items for users.

Professors Boularias, Aanjaneya and Yu receive NSF NRI grant

Congratulations to Professors Abdeslam Boularias, Mridul Aanjaneya, and Jingjin Yu for having their project titled "Robust and Efficient Physics-Based Learning and Reasoning in Degraded Environments" recommended for funding by the National Science Foundation.The $1.5 million, four-year project will perform fundamental research into developing and integrating physics-driven reasoning and planning techniques to enable autonomous robots to manipulate unknown irregular objects and navigate in unstructured, dynamic environments. The developed techniques will be deployed on RoboMantis - a four-legged, wheeled robot that can assist in first-response missions. The project will fill the important gap between existing research on learning models of unknown objects from data and research on developing adequate simulation tools for robotic manipulation and locomotion by answering three fundamental questions: 1) How to efficiently simulate the effects of robotic actions on objects with uncertain models? 2) How to use physics simulation tools to plan manipulation and locomotion strategies for navigating in unstructured terrains? and, 3) How to learn physical models of objects on the fly? The project builds on top of progress in computer vision, physics simulation, and planning, towards developing an efficient toolset for robotic navigation in rubble.  

In Memoriam: Marvin Paull

Marvin Cohen Paull,  Professor Emeritus, Department of Computer Science, Rutgers – The State University of New Jersey and Pioneering Researcher and Developer of Switching Network Systems at the AT&T Bell Laboratories, NJ   Marvin Cohen Paull was born on May 5, 1929 to Samuel (ne Yampolsky) and Jean Cohen Paull.  He grew up with his older sister Deborah, who predeceased him, in Brooklyn, The Bronx, and Queens.  Marvin enlisted in the Navy after high school, then used the GI Bill to attend the Clarkson College of Technology where he was awarded the BSEE in 1952. He was a member of Tau Beta Pi and Eta Kappa Nu. Marv Paull joined the Bell Telephone Laboratories in 1953, where he worked on the development of the first electronic switching system as well as on magnetic logic, sequential machines and systems, macro assemblers, and compilers.  He published many articles in the Bell System Technical Journal. He was co-author of the Paull -Unger theorem in switching theory – “Minimizing the Number of States in Incompletely Specified Sequential Switching Functions” in the IRE Trans Electronic Computers, September 1959, and co-authored “Boolean Functions Realizable with Single Threshold Devices” with E.M. McCluskey in the Proceedings of the IRE, July 1960. He left Bell Labs when his department moved out of state, and joined the computer theory group at RCA Laboratories, while teaching a graduate course on advance programming at Columbia University. In 1969, Marv Paull joined Rutgers University to help form the expanding graduate program in the Department of Computer Science (DCS). Marvin completed 40 years of service, retiring as Professor Emeritus.  At Rutgers Marv Paull worked on programming languages, parallel systems and computer architectures. He taught graduate courses on the Syntax and Semantics of Programing Languages, and the Theory of Finite State Machines as well as many undergraduate courses. He supervised the dissertations of Paul Murphy, John Franco, Barbara Ryder, Marie-Therese Daulard, and Arthur Berman. He authored the book Algorithm Design: A Recursion Transformation Framework, Wiley, 1986, and co-authored the seminal paper “Elimination Algorithms for Data Flow Analysis” with Barbara Ryder (ACM Computing Surveys, September 1986). Marvin had an enduring love for the early 1960’s folk culture - Dylan and Cohen (especially his “Suzanne”) and Judy Collins and was really a kind and gentle soul. He loved to ski when younger. He often baked challah for family gatherings. Marvin Paull passed away at Parker Memorial Home in Piscataway, NJ on June 14, 2021. He is survived by his two sons, Chris Paull (Diane Shemenski) and Eric Paull and was the former husband of their mother, Charlene Thiel Paull.  Marvin encouraged his sons in whatever they chose to do. He is also survived by grandchildren Gerik and Annika Paull in California, nieces Stephanie  Myara and Rachel White, and his longtime companion, Susan Marchand and her daughter Shoshana and grandchildren who considered him family.  Marvin donated his body to the Anatomical Association at Rutgers Medical School.  A memorial will be planned for later in the summer. Contributions in his memory can be made to the Southern Poverty Law Center, Elijah’s Promise soup kitchen in New Brunswick, NJ or a charity of your choice.

Pennock, David

01:198:310 Data Science Capstone Project

01:198:462 Introduction to Deep Learning

01:198:461 Machine Learning Principles

01:198:210 Data management for Data Science

Huang, Yipeng

Wang, Hao

Prof. Wang receives 2020 Amazon Research Award in Artificial Intelligence

Prof. Hao Wang was awarded the highly selective Amazon Research Award (ARA) in Artificial Intelligence for his proposed project titled: "Structured domain adaptation with applications to personalization and forecasting". For the list of 2020 ARA awardees, see:

Profs. Santosh Nagarakatte and Mridul Aanjaneya awarded NSF Grant for their Project on Correctly Rounded Math Libraries

Congratulations to Profs. Santosh Nagarakatte and Mridul Aanjaneya, who have received an NSF SHF Small Grant for their project titled "Techniques for Generating Correctly Rounded Math Libraries", for an amount of $499, 979, covering a three-year period starting from 06/1/2021. Every programming language needs math libraries, which provide implementations of elementary functions for the floating-point representation and its variants. This project aims to develop correctly rounded math libraries for a wide range of representations that approximate real numbers. This project's novelty lies in creating polynomial approximations that produce the correctly rounded value of an elementary function f(x) (i.e., the value of f(x) rounded to the target representation) rather than the real value of f(x). It provides more margin to identify correct polynomials while generating efficient implementations. This project structures the task of generating efficient polynomial approximations that produce correctly rounded results as a linear-programming problem. It advances the state-of-the-art in approximating elementary functions for a large number of data types while allowing domain scientists to experiment with both precision and dynamic range of the data types.  More details can be found on the National Science Foundation's webpage at  

Prof. Yu receives 2020 Amazon Research Award in Robotics

Prof. Jingjin Yu was awarded the highly selective Amazon Research Award (ARA) in Robotics for his proposed project titled: "Pushing the limits of efficient and optimal multi-agent path finding through exploring space utilization optimization and adaptive planning horizon heuristics". The award provides a $80,000 gift.      The ARA project will develop novel methods for near-optimally solving Multi-Agent Path Finding (MAPF) problems. The majority of practical MAPF algorithms adapt a decoupled scheme that operates in two phases: (1) initial path planning for individual agents agnostic to potential collisions, and (2) path execution with local conflict resolution. Our proposed algorithm, adhering to the decoupled MAPF scheme, will be built on two key heuristics to significantly boost the performance of the two phases, respectively: decentralized path diversification for better global space utilization in the initial planning phase and adaptive planning horizon for bounding computation efforts for path conflict resolution. Our preliminary research has demonstrated that precursors to the proposed heuristics are effective as individual sub-routines in MAPF pipelines. In this project, we will develop these heuristics to their full potential and integrate them to yield a new MAPF algorithm expected to outperform current state-of-the-art methods in solving challenging MAPF problems. For the list of 2020 ARA awardees, see:    
Results 1 - 20 of 1137