Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 13403-13404· 0 citations· 5 references
TL;DR
This workshop aims to provide a forum for advancing tensor methods and applying them to various applications at the intersection of data mining and modern machine learning to foster an interactive environment for researchers to exchange ideas and build connections across communities.
Abstract
Tensor methods have played a central role in analyzing multi-dimensional data across a wide range of real-world applications. At the same time, these methods provide low-rank representations, which enable trustworthy and parsimonious machine learning systems. However, even though they hold great promise, tensor methods remain relatively underexplored in the context of modern neural architectures and foundation models. This workshop aims to provide a forum for advancing tensor methods and applying them to various applications at the intersection of data mining and modern machine learning. Supported by organizers and keynote speakers with broad expertise across machine learning, signal processing, and data mining, the workshop aims to foster an interactive environment for researchers to exchange ideas and build connections across communities.
Developing nonlinear models that are both expressive and computationally efficient remains a challenge in machine learning and nonlinear system identification. Tensor network kernel machines (TNKM) address this challenge by combining nonlinear feature representations with compact low-rank tensor-network parameterizations. However, practical and extensible software frameworks for developing TNKM models remain limited. In this work, we introduce"tnkm", an open-source Python library for constructing and training TNKM models using JAX. The library provides a unified interface for combining different feature maps, tensor-network architectures, and optimization strategies, including alternating least squares and gradient-based methods. We demonstrate the capabilities of"tnkm"on nonlinear benchmark problems, showing that the implemented models achieve competitive prediction accuracy while retaining compact parameterizations and efficient training. The proposed framework facilitates reproducible development and application of tensor-network-based learning methods.
This paper proposes a novel Tensor Train (TT)-based tensor-on-tensor regression optimization framework for variable selection based on mode-1 hyperslice sparsity. The formulation incorporates an l2,0-regularized term on the first TT-core while imposing Stiefel manifold constraints on the remaining M−1 TT-cores. Leveraging the property that the group sparsity of the first core is equivalent to the hyperslice sparsity of the global structure, we establish theoretical guarantees for the uniform variable-selection consistency of the proposed model. To efficiently solve the proposed model, we design an alternating iterative algorithm equipped with a preconditioned metric and prove its convergence to a critical point. Extensive numerical experiments on both synthetic and real-world datasets demonstrate that the numerical solutions generated by our algorithm exhibit exact support recovery in practice, tightly aligning with our theoretical analysis.
This work presents a method to accelerate the optimization of learning high dimensional functions using deep neural network (DNN), and studies the effect of adding features which distill pretrained DNN into TNs using a discretize and decompose strategy.
This thesis builds on an existing diagnostics toolkit mainly for t-SNE and UMAP and turns it into a more accessible package for interested practitioners, while also extending it with diagnostics tools.
Kasra Amirani, Sem Huisman, Dr. E.P.L. van Nieuwenburg· 0 citations
The growing availability of tensor-valued data across multiple institutions creates opportunities for collaborative analysis, but also raises challenges related to data privacy, high dimensionality, and client heterogeneity. This paper introduces a personalized federated tensor regression framework that addresses all three simultaneously. Each client's coefficient tensor is decomposed into a globally shared low-Tucker-rank component and a locally sparse deviation, estimated via a two-stage privacy-preserving procedure. We establish finite-sample upper bounds and minimax lower bounds that quantify the privacy-accuracy trade-off, and prove the consistency of the supporting initialization and rank-selection steps. Simulation studies confirm that the federated approach improves estimation and prediction over purely local methods, especially when per-client data are scarce, and an MRI-based ADHD study illustrates its strong performance under real privacy constraints.