Welcome to visit Teddy's homepage!
- We're hiring: TWO Postdoc Researcher Openings for a DARPA project (2019-2023) (Lingfei is the PI in IBM). We are looking for highly-motivated talented researchers to work in a world-class team collaborated with MIT, Columbia, and IBM Research on a high-impact project. Please apply here before 10/15/2019!
- Upcoming talks: Tutorial in Deep Learning on Graphs in AAAI'20, Keynote talk at SDM2020 WSUL Workshop, Keynote talk at CVPR2020 DIRA Workshop.
- Welcome to submit your works to our AAAI'20 Workshop on "Deep Learning on Graphs: Methodologies and Applications (DLGMA’20)", submission deadline is 11/15/2019!
- Welcome to submit your works to our IEEE BigData'19 Workshop on "Deep Graph Learning: Methodologies and Applications (DGLMA’19)", submission deadline is 10/01/2019!
- Welcome to submit your works to Our KDD'19 Workshop on "Deep Learning on Graphs: Methods and Applications (DLG’19)", submission deadline is 05/05/2019! Our DLG'19 workshop has attracted 400+ attendees to listen five world-class top researchers/industrial leaders in ML/DL/NLP!
- Welcome to submit your works to The Third International Conference on AI + Adaptive Education. Please see our CFP and early bird gets prioritized travel support (submit by 04/1)!
Lingfei Wu is a Research Staff Member in the IBM AI Foundations Labs, Reasoning group at IBM T. J. Watson Research Center. He earned his Ph.D. degree in computer science from College of William and Mary in August 2016, under the supervision of Prof. Andreas Stathopoulos. He is a research team leader (consisting of 10+ research staff members) for several research projects (we named AI Challenges inside IBM Research), including Deep Learning on Graphs for AI. He has served as the PI in IBM for several federal agencies such as DARPA and NSF (more than $1.8M). He is also an IBM Co-PI of the MIT-IBM Watson AI Lab Award (2018 and 2019) for projects themed "Intelligent Multi-Scale Design of De Novo Proteins to Enhance Food Security".
His research interests lie at the intersection of Machine Learning(Deep Learning), Representation Learning, and Natural Language Processing, with a particular emphasis on the fast-growing subjects of Graph Neural Networks and its extensions on new application domains. Lingfei has published more than 50 top-ranked conference and journal papers, including but not limited to NIPS, ICML, ICLR, AISTATS, KDD, ICDM, NAACL, EMNLP, IJCAI, AAAI, and SIAM Journal on Scientific Computing. He is also a co-inventor of more than 20 filed US patents. He was the recipients of the Best Paper Award in IEEE ICC'19 and KDD workshop on DLG'19, and the Best Student Paper Award in AIAED'19 and KDD workshop on DLG'19. Lingfei's research has been featured in numerous media outlets, including NatureNews, YahooNews, Venturebeat, TechTalks, SyncedReview, Leiphone, QbitAI, MIT News, IBM Research News, and SIAM News.
Currently, Lingfei serves as an Associate Editor for ACM Transactions on Knowledge Discovery from Data. He has organized or served as Poster co-chairs of IEEE BigData'19, Tutorial co-chairs of IEEE BigData'18, Workshop co-chairs of Deep Learning on Graphs (including AAAI'20 Workshop, IEEE BigData'19, KDD'19 Workshop), and Track co-chairs of The Third International Conference on AI + Adaptive Education (AIAED'19). In addition, he has regularly served as a SPC/TPC of the following major AI/ML/DL/DM/NLP conferences including NIPS, ICML, ICLR, ACL, IJCAI, AAAI, and KDD. Lingfei regularly reviews the manuscripts for the following first-rate journals: SIAM Journal on Scientific Computing, SIAM Journal on Matrix Analysis and Applications, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Signal and Information Processing over Networks, IEEE/ACM Transactions on Audio, Speech, and Language Processing, IEEE Transactions on Big Data, IEEE Transactions on Parallel and Distributed Systems, ACM Transactions on Management Information Systems, Data Mining and Knowledge Discovery, Pattern Recognition, and Future Generation Computer Systems.
Press coverage of my research:
- Reinforcement Learning on Software Defined Networking: <IBM Research AI Blog>
- Text Adversarial Attacks: <NatureNews> <Venturebeat> <TechTalks> <SyncedReview>
- AI for Food Security: <MIT News> <MIT-IBM Lab News> <MIT Quest for Intelligence Research>
- Graph Neural Networks: <Yahoo News> <Leiphone> <QbitAI> <IBM Research AI Blog>
- Natural Language Progressing, Setence/Document Embeddings: <IBM Research AI Blog>, <IBM Research AI Blog>
- Graph Learning and Network Analysis: <IBM Research AI Blog>
- Scientific Computing and High-Performance Computing: <SIAM NEWS>
12/2019: Our paper on RL Based Graph2Seq for Question Generation is accepted by ICLR'20! Graph2Seq has been proved again to perform better than Seq2Seq!
12/2019: Lingfei Wu has been invited as SPC of KDD'20, IJCAI'20, and AAAI'20!
11/2019: Honored and humbled to lead a team to receive 2019 IBM Research Accomplishment Award for contributions of fundamental research in graph neural network and its applications in a wide range of AI tasks!
11/2019: Delighted to receive NSF funding (Co-PI in IBM) of EFRI C3 SoRo for our proposal "EFRI C3 SoRo: Functional-Domain Soft Robots Precisely Controlled by Quantitative Dynamic Models and Data"!
11/2019: Lingfei Wu has been selected as one of the representatives at IBM to attend Yoshua Bengio's Turing Award event in Montreal at MILA!
11/2019: Lingfei Wu has been appointed as an Associate Editor for ACM Transactions on Knowledge Discovery from Data! Welcome to submit your works to this top-ranked data mining journal!
10/2019: Keynote/Invited talks on China International Symposium on Artificial Intelligence and Education in Hefei China, International Workshop on Machine Learning & Artificial Intelligence in Paris France, visiting UCLA, UCSB, Nanjing University, Zhejiang University, and Fudan University.
09/2019: Our tutorial proposal "Graph Neural Networks: Models and Applications" has been accepted by IEEE AAAI 2020! If you are working on GNNs or want to know more about GNNs, welcome to attend our tutorial in February!
09/2019: Our paper on Kernelized Graph Matching is accepted by NeurIPS'19 as a spotlight talk paper, acceptance rate: 3% (200/6743)!
08/2019: Our GNN workshop "Deep Learning on Graphs: Methodologies and Applications (DLGMA’19)" has been accepted by IEEE AAAI 2020! Welcome to submit your works to our workshop!
08/2019: One paper on Deep Classifier Cascades for Open World Recognition is accepted by CIKM'19!
08/2019: Two papers on Dynamic-Graph-to-Sequence Interpretable Learning and Feature Dependency Pattern Mining are accepted by the ICDM'19!
08/2019: Our DLG'19 workshop in KDD 2019 has attracted 400+ attendees to listen five world-class top researchers/industrial leaders in ML/DL/NLP!
08/2019: Received the MIT-IBM Watson AI Lab Award (2019) for the proposal entitled "Intelligent Multi-Scale Design of De Novo Proteins to Enhance Food Security"!
06/2019: Three papers on Graph Neural Networks for RDF-to-Text, Semantic Parsing, and Graph Translation are accepted by the KDD 2019 Workshop on Deep Learning on Graphs: Methods and Applications!
05/2019: Our workshop paper on Graph Neural Networks for Conversational Machine Comprehension is accepted by the ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data!
05/2019: Our SysML 2019 paper on text adversarial attack and training is covered by NatureNews!
05/2019: Our AIAED2019 paper entitled "Toward Automated Queries Generation from Natural Language Description Using Graph Neural Networks" has won the BEST STUDENT PAPER Award! Big congrats to the team!
05/2019: Our ICC2019 paper entitled “DQ Scheduler: Deep Reinforcement Learning Based Controller Synchronization in Distributed SDN,” has won the BEST Paper Award! Big congrats to the team!
05/2019: One paper entitled "Similarity Preserving Representation Learning for Time Series Clustering" has been accepted by IJCAI 2019! Please see sister work on time-series embedding (RWS at AIStats 2018)
05/2019: Honored to be invited and delivered another talk about Graph-to-Sequence Learning in Natural Language Processing on SMSD Seminar Series at MIT !
05/2019: Our GNN workshop "Deep Graph Learning: Methodologies and Applications (DGLMA’19)" has been accepted by IEEE BigData 2019! Welcome to submit your works to our workshop!
04/2019: Two papers about efficient graph-level embeddings from node embeddings and scalable string embeddings for symbolic sequence inputs are accepted by KDD 2019!
04/2019: Honored to be invited and delivered another talk about Graph-to-Sequence Learning in Natural Language Processing on CSCE Graduate Seminar at TAMU!
04/2019: One paper entitled "Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications" is accepted by ICML 2019!
04/2019: Honored to be invited and delivered a talk about Graph-to-Sequence Learning in Natural Language Processing on CSE Lecture Series at MSU!
04/2019: Our paper on Scalable Attributed Graph Embeddings is accepted by the ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds!
03/2019: Our KDD workshop "Deep Learning on Graphs: Methods and Applications (DLG'19)" has been accepted by KDD 2019! See you all on Deep Learning Day at KDD 2019!
03/2019: Delivered a talk for our SysML'19 paper entitled "Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification" at Stanford University!
03/2019: Delivered a seminar talk entitled "Graph-to-Sequence Learning in Natural Language Processing" in the Computer Science and Engineering Department at University of Notre Dame!
2/2019: Two papers about Text Style Transfer and Memory Networks for KBQA are accepted by NAACL'19!
1/2019: One paper entitled "DQ Scheduler: Deep Reinforcement Learning Based Controller Synchronization in Distributed SDN" is accepted by ICC 2019!
1/2019: RC_RB code was just released in Github! RC_RB is a simple code for scaling up spectral clustering on large-scale datasets using Random Binning and PRIMME. See our paper and IBM Research AI Blog for more details!
1/2019: One paper entitled "Discrete Attacks and Submodular Optimization with Applications to Text Classification" is accepted by SYSML 2019!
1/2019: Our MIT-IBM research project (Co-PI) - AI-Based Novel Protein Design is listed as featured projects.
12/2018: Our tutorial entitled "Unsupervised Feature Representation Learning via Random Features for Structured Data: Theory, Algorithm, and Applications" was delivered on IEEE Big Data 2018!
11/2018: WME code code was just released in Github! WME is a simple code for generating universal text embedding for sentence, paragraph, and document. See our paper and IBM Research AI Blog for details!
11/2018: One paper entitled "From Node Embedding to Graph Embedding: Scalable Global Graph Kernel via Random Features" is accepted as an oral talk by NIPS18' workshop on Relational Representation Learning!
11/2018: One work in EMNLP'18 on universal sentence/document embedding is featured on IBM Research AI Blog!
11/2018: Two of our EMNLP'18 works on semantic parsing and natural language generation are featured on IBM Research AI Blog!
10/2018: One paper entitled "Incomplete Label Multi-task Deep Learning for Spatio-temporal Event Subtype Forecasting" is accepted by AAAI'19!
09/2018: RB_GEN codes were just released in Github! RB_GEN is a simple package for generating random binning features for solving large-scale kernel classification, regression, and clustering. See our KDD16 and KDD18 papers for more details!
09/2018: Honored to be selected as one of the top 30% highest-scoring reviewers at NIPS'18!
09/2018: Our KDD work on an end-to-end approach for scaling up spectral clustering is featured on IBM Research AI Blog!
08/2018: Three papers about unsupervised document embedding, SQL-to-Text, Text-to-logicform are accepted by EMNLP'18!
08/2018: Received IBM Second level plateau Invention Achievement Award, 2018
05/2018: One paper entitled "Scalable Spectral Clustering Using Random Binning Features" gets accepted as an oral paper by KDD'18!
05/2018: Received IBM Manager's Choice Award, 2018!