Timeline
The Reconciled Polynomial Network version 2 (RPN 2) paper is released. RPN 2 focuses on data interdependence function learning and can serve as the backbone to unify different base models into one canonical representation, including CNN, RNN, GNN and Transformer.
The tinyBIG documentation website is online. tinyBIG is a website hosting the documentations, tutorials, examples and the latest updates about the tinybig library.
The Reconciled Polynomial Network (RPN) paper is released. RPN has a very general architecture and can be used to build models with various complexities, capacities, and levels of completeness, which all contribute to the correctness of these models. In addition, RPN can also serve as the backbone to unify different base models into one canonical representation, including PGMs, kernel SVM, MLP and KAN.
The tinybig Python Library source code is released at github. The package has also been posted to PyPI, which is ready for downloading and installing.
Grateful to receive an NSF award (IIS-2106972) as the PI to support our research work on self-supervised recommender system learning.
A collaborated research paper entitled "Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer" is accepted by CIKM as a regular paper.
Our research team has been relocated to Davis at California, and will be hosted at the Computer Science department at UC Davis.
Three research papers from IFM Lab entitled Fake News Detection on News-Oriented Heterogeneous Information Networks through Hierarchical Graph Attention, Ripple Walk Training: A Subgraph-based training framework for Large and Deep Graph Neural Network, BGADAM: Boosting based Genetic-Evolutionary ADAM for Convolutional Neural Network Optimization are accepted by IJCNN.
One research paper from IFM Lab entitled Label Contrastive Coding based Graph Neural Network for Graph Classification is accepted by DASFAA.
The Advanced Database course will be offered to the graduate students in 2021 Spring. This course will cover advanced topics about database systems. We are calling for enrollment.
One collaborated research paper entitled Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs is accepted by AAAI.
One collaborated research paper entitled Few-shot Radiology Report Generation for Rare Diseases is accepted by BIBM.
One research paper from IFM Lab entitled DEAM: Adaptive Momentum with Discriminative Weight for Stochastic Optimization is accepted by ASONAM.
One collaborated research paper entitled AutoCite: Multi-Modal Representation Fusion for Contextual Citation Generation is accepted by WSDM.
One research paper from IFM Lab entitled Text Graph Transformer for Document Classification is accepted by EMNLP as a short paper.
The Database course will be offered to the undergraduate students in 2020 Fall. This course will cover topics like "ER model", "relational database", "SQL", "indexing", "transaction management", etc. We are calling for enrollment.
Three research papers entitled "Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection", "Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning", and "PERFECT: A Hyperbolic Embedding for Joint Social Network Alignment" from IFM Lab are accepted by ICDM as regular full papers.
One research paper from IFM Lab EnsemFDet: An Ensemble Approach to Fraud Detection based on Bipartite Graph is accepted by the ICDE.
One collaborated research paper CommDGI: Community Detection Oriented Deep Graph Infomax is accepted by CIKM.
One research paper from IFM Lab Get Rid of Suspended Animation: Deep Diffusive Neural Network for Graph Representation Learning is accepted by the ICML workshop on Graph Representation Learning and Beyond (GRL+).
One research paper from IFM Lab Scalable Heterogeneous Social Network Alignment through Synergistic Graph Partition is accepted by HT 2020.
Two collaborated research papers Attention- based Multi-level Feature Fusion for Named Entity Recognition and BANANA: when Behavior ANAlysis meets social Network Alignment are accepted by IJCAI 2020.
One research preprint paper from IFM Lab GRAPH-BERT: Only Attention is Needed for Learning Graph Representations is released. The corresponding model Source code of Graph-Bert is also released at github.
A new course entitled Deep Learning and Applications will be offered to the graduate students in 2020 Spring. This course will cover some advanced topics like "deep learning & optimization", "graph mining", "natural language processing" and "recommender system", etc. We are calling for enrollment.
One collaborated research paper Learning Signed Network Embedding via Graph Attention is accepted by AAAI 2020 as a full paper. One paper from IFM Lab entitled Heterogeneous Deep Graph Infomax is accepted by the Deep Learning on Graphs: Methodologies and Applications workshop co-located with AAAI.
Three research papers from IFM Lab LATTE: Application Oriented Network Embedding and Deep Diffusive Neural Network based Fake News Detection from Heterogeneous Social Networks and JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation are accepted by IEEE BigData 2019.
One research paper IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification from IFM Lab is accepted by NIPS 2019 Graph Representation Learning Workshop.
Yixin Chen and Haopeng Zhang join IFM Lab as PhD students starting from Fall 2019. Chenlu Wang and Haoran Yang join IFM Lab as visiting students since the summer of 2019.
The Database course will be offered to the undergraduate students in 2019 Fall. This course will cover topics like "ER model", "relational database", "SQL", "indexing", "transaction management", etc. We are calling for enrollment.
One research paper FAKEDETECTOR: Effective Fake News Detection with Deep Diffusive Neural Network from IFM Lab is accepted by ICDE 2020 in the 1st Round.
One collaborated paper "Collective Link Prediction Oriented Network Embedding with Hierarchical Graph Attention" is accepted by CIKM 2019.
IFM Lab tutorial article Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview is released, which provides an introduction to the latest graph neural networks, including IsoNN, SDBN, LF&ER, GCN, GAT, DifNN, GNL, GraphSage and seGEN. Latest preprints of IsoNN and GNL first-authored by Lin Meng and Yixin Chen from IFM Lab are also released.
IFM Lab tutorial article Cognitive Functions of the Brain: Perception, Attention and Memory is released, which provides an introduction to the brain cognitive functions, including perception, attention and memory.
IFM Lab tutorial article Basic Neural Units of the Brain: Neurons, Synapses and Action Potential is released, which provides an introduction to the brain basic neural units, including neurons, synapses, and action potential.
One collaborated paper "Learning Network Embedding with Community Structural Information" is accepted by IJCAI 2019.
IFM Lab tutorial article Secrets of the Brain: An Introduction to the Brain Anatomical Structure and Biological Function is released, which provides an introduction to the brain anatomical structure and function, as well as its surrounding sensory systems.
IFM Lab tutorial article Derivative-Free Global Optimization Algorithms: Population based Methods and Random Search Approaches is released, which provides an introduction to the derivative-free global optimization algorithms with potential applications on training deep learning models. The covered algorithms include population based methods, e.g., GA, SCE, DE, PSO, ES, CMA-ES, and random search based approaches, e.g., hill-climbing and simulated annealing.
IFM Lab tutorial article Derivative-Free Global Optimization Algorithms: Bayesian Method and Lipschitzian Approaches is released, which provides an introduction to the derivative-free global optimization algorithms with potential applications on training deep learning models. The covered algorithms include Bayesian method and Lipschitzian approaches, e.g., Shubert-Piyavskii algorithm, DIRECT, LIPO and MCS.
Two collaborated papers "Deep Distribution Network: Addressing the Data Sparsity Issue for Top-N Recommendation" and "Gated Spectral Units: Modeling Co-evolving Patterns for Sequential Recommendation" are accepted by SIGIR 2019.
One collaborated research paper "Missing Entity Synergistic Completion across Multiple Isomeric Online Knowledge Libraries" is accepted by IJCNN 2019.
IFM Lab tutorial article Gradient Descent based Optimization Algorithms for Deep Learning Models Training is released, which provides a comprehensive introduction to the gradient descent based learning algorithms for deep learning models. The covered algorithms include GD, SGD, Mini-batch GD, Momentum, NAG, Adagrad, RMSprop, Adadelta, Adam, Nadam, and Gadam.
One research paper from IFM Lab "Meta Diagram based Active Social Networks Alignment" is accepted by ICDE 2019 as a short paper.
A textbook "Broad Learning Through Fusions: An Application on Social Networks" from IFM Lab is published by Springer. This book offers a clear and comprehensive introduction to broad learning, one of the novel learning problems studied in data mining and machine learning. Pre-order is available via both Springer and Amazon.
A new course entitled Advanced Data Mining will be offered to the graduate students in 2019 Spring. This course will cover some advanced topics like "network mining", "graph mining", "deep learning", "broad learning", "text mining" and "recommender system", etc. We are calling for enrollment.
The DataLiber open data platform has been released online. DataLiber helps you share, trade and customize data with AI experts/institutes all over the world. Once you join DataLiber, you'll be able to access the data, tasks, forum, experts, institutes, and more.
One research papers "Data-driven Blockbuster Planning on Online Movie Knowledge Library" is accepted by IEEE BigData 2018.
The Database course will be offered to the undergraduate students in 2018 Fall. This course will cover topics like "ER model", "relational database", "SQL", "indexing", "transaction management", etc. We are calling for enrollment.
One collaborated paper entitled " A Self-Organizing Tensor Architecture for Multi-View Clustering " is accepted by the 2018 ICDM.
Miss. Lin Meng and Mr. Jiyang Bai join IFM Lab as new PhD students starting from Fall 2018.
One collaborated paper entitled "Spectral Collaborative Filtering " is accepted by the 2018 RecSys proceedings as a Long Paper.
Grateful to receive an NSF award (IIS-1763365) as the PI to support our research work on heterogeneous social network representation learning.
One collaborated paper entitled " You Are How You Drive: Peer and Temporal-Aware Representation Learning for Driving Behavior Analysis " is accepted by KDD 2018.
One collaborated paper entitled "Multi-view Fusion Through Cross-Modal Retrieval" is accepted by ICIP 2018.
One collaborated paper entitled "Multi-view Collective Tensor Decomposition for Cross-modal Hashing " is accepted by ICMR 2018.
Two collaborated papers entitled "Modeling the Interaction Coupling of Multi-View Spatiotemporal Contexts for Destination Prediction" and "Ensemble-Spotting: Prioritizing Vibrant Communities via POI Embedding with Multi-view Spatial Graphs" are accepted by SDM 2018.
Mr. Yuxiang Ren joins IFM Lab as a PhD student starting from Spring 2018.
A new course entitled Social Network Mining will be offered to the graduate students in 2018 Spring. This course will cover some advanced topics like "social network mining", "graph mining", "deep learning", "broad learning", "text mining" and "recommender system", etc. We are calling for enrollment.
Two research papers "Inverse Extreme Learning Machine for Learning with Label Proportions" and "Contaminant Removal for Android Malware Detection Systems" are accepted by IEEE BigData 2017.
Our research paper BL-MNE: Emerging Heterogeneous Social Network Embedding through Broad Learning with Aligned Autoencoder is accepted by ICDM 2017 as a FULL paper.
Two research papers Broad Learning based Multi-Source Collaborative Recommendation and BL-ECD: Broad Learning based Enterprise Community Detection via Hierarchical Structure Fusion are accepted by CIKM 2017.
IFM Lab is a research oriented academic laboratory directed by Prof. Jiawei Zhang, providing the latest information on fusion learning and data mining research works. IFM Lab will be hosted at the Computer Science department at Florida State University.
