Important Dates


Submission Deadline: April 26, 2020 August 1, 2020
Acceptance Notification: May 26, 2020 September 1, 2020
Camera-ready Deadline: June 10, 2020 September 15, 2020
Workshop Date: July 11, 2020 January, 2021 (exact dates and duration to be determined)


Submission Guidelines


The workshop solicits the following submissions.

  • Regular paper (up to 7 pages) describing original research work that have not been published before.
  • Position paper (up to 4 pages) reporting preliminary research findings or discussing inspiring and new directions.
  • Extended abstract (2 pages) highlighting significant works that have been published.

Formatting guidelines, LaTex styles and Word template: https://www.ijcai.org/authors_kit



Submission site: https://cmt3.research.microsoft.com/TNRML2020



The reviewing process can be double-blind or single-blind depending on the submissions. All submissions will be peer reviewed and evaluated based on technical contribution, originality, relevance to areas of interest, and presentation clarity. Papers may be accepted for either oral or poster presentation. Accepted papers will be published online on the workshop website.


Topics of Interest


We are soliciting contributions that address a wide range of theoretical and practical issues including, but not limited to

  • Fundamental theory and algorithm of tensor networks
  • Scalable and efficient algorithms for tensor network representations
  • Structure learning of tensor networks
  • Tensor networks in deep learning
  • Tensor graphical model
  • Tensor networks for data completion
  • Multi-view, multi-task and multi-modal learning using tensor networks
  • Tensor networks in optimization and sparse coding
  • Tensor networks GPU/FPGA computation architectures
  • Supervised learning using tensor network representation
  • Unsupervised learning and dimensionality reduction via tensor networks
  • Tensor networks in reinforcement learning
  • Tensor network representations for generative model
  • Tensor decomposition for subspace clustering and co-clustering
  • Robust low-rank matrix/tensor decomposition
  • Tensor networks in graphical neural network
  • Tensor networks in long-term memory modeling
  • Deep neural tensor network
  • Tensor network for graph signal/data processing
  • Tensor network computation in terabyte scale
  • Library for tensor network calculations and specified applications
  • Low-rank matrix decomposition for multi-incomplete labels
  • Tensor networks in weakly supervised learning

Applications of TNs to

  • Object detection and image segmentation
  • Video analysis and human action recognition
  • Biomedical image processing
  • Hyperspectral image analysis
  • Natural language processing
  • 3D modeling and SLAM
  • Multimodal sentiment analysis
  • Wireless communication and adaptive networking
  • Information security and privacy protection
  • Computational photography
  • Neural network compression
  • Chemistry and quantum physics