Interaction Tensor
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Tractable Shapley Values and Interactions via Tensor Networks
Announce Type: replace Abstract: We show how to replace the O(2^n) coalition enumeration over n features behind Shapley values and Shapley-style interaction indices with a few-evaluation scheme on a tensor-network (TN) surrogate: TN-SHAP. The key idea is to represent a predictor's local behavior as a factorized multilinear map, so that coalitional quantities become linear probes of a coefficient tensor. TN-SHAP replaces exhaustive coalition sweeps with just a small number of targeted...
TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions
arXiv:2606.01540v1 Announce Type: new Abstract: Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation involves a function defined over an exponentially large space of subsets. We propose TN-SHAP-G, a framework that exploits structure in graph-structured inputs to compute Shapley values and higher-order interaction indices efficiently. Given a predictor and a fixed masking scheme, TN-SHAP-G learns a...
What Do Students Learn? A Feature-Level Analysis of Dark Knowledge
arXiv:2606.03052v1 Announce Type: new Abstract: Knowledge Distillation (KD) is a powerful tool for model compression, yet the precise mechanisms by which student models acquire feature representations remain underexplored. In this work, we analyze student feature learning using the Interaction Tensor framework. Our analysis reveals that effective KD acts as a regularizer that prunes low-frequency, sample-specific features, encouraging the student to rely on a compact set of highly reusable...
Beyond Additive Decompositions: Interpretability Through Separability
Announce Type: replace Abstract: Interpretable machine learning requires models that are accurate and structurally faithful to the data. Existing explainability methods rely heavily on additive representations (e.g., Generalized Additive Models (GAMs), SHapley Additive exPlanations (SHAP), functional ANOVA), which can suffer from signal cancellation and off-support extrapolation in the presence of strong interactions. We propose Tensor Separation Learning (TSL), a regression model that...
Beyond Additive Decompositions: Interpretability Through Separability
arXiv:2605.31200v1 Announce Type: new Abstract: Interpretable machine learning requires models that are accurate and structurally faithful to the data. Existing explainability methods rely heavily on additive representations (e.g., Generalized Additive Models (GAMs), SHapley Additive exPlanations (SHAP), functional ANOVA), which can suffer from signal cancellation and off-support extrapolation in the presence of strong interactions. We propose Tensor Separation Learning (TSL), a regression...
New discovery upends an 80-year-old theory of turbulence
New discovery upends an 80-year-old theory of turbulence Scientists have found a way to steer the flow of turbulent energy, overturning a long-held rule. - Date: - June 3, 2026 - Source: - University of Pittsburgh - Summary: - Researchers discovered a way to reverse the direction of energy flow in turbulence, challenging a theory that has stood for more than 80 years.
Exact solution of the two-dimensional (2D) Ising model at an external magnetic field
arXiv:2512.16935v4 Announce Type: replace Abstract: The exact solution of the two-dimensional (2D) Ising model at an external magnetic field is derived by a modified Clifford algebraic approach. At first, the transfer matrices are analyzed in three representations, i.e., Clifford algebraic representation, transfer tensor representation and schematic representation, to inspect nonlocal effects in this many-body interacting system. It is ensured that nontrivial topological structures exist in...
Process-tensor approach to full counting statistics of charge transport in quantum many-body circuits
Announce Type: replace-cross Abstract: We introduce a numerical tensor-network method to compute the statistics of the charge transferred across an interface partitioning an interacting one-dimensional many-body lattice system with $U(1)$ symmetry. Our approach is based on a matrix-product state representation of the process tensor (also known as influence functional or influence matrix) describing the effect of the bulk system on the degrees of freedom at the interface, allowing us to...
Tensor gradient flow with quasi-entropy for smectic liquid crystals and discretizations keeping coupled physical constraints
arXiv:2606.00659v1 Announce Type: cross Abstract: A gradient flow for the concentration and a $2\times 2$ tensor is constructed to describe smectic liquid crystals. The free energy consists of the entropy term and interaction term involving squared second order spatial derivatives. The entropy term incorporates the concentration in the quasi-entropy originally proposed for the tensor only, which is a strictly convex and lower semicontinuous function imposing coupled constraints between the...
Spectra-Guided Neural Tucker Factorization
arXiv:2606.00584v1 Announce Type: cross Abstract: This paper proposes Spectra-Guided Neural Tucker Factorization (SG-NTF) for High-Dimensional and Incomplete (HDI) tensor completion. Circumventing discrete representational limits, SG-NTF maps scalar timestamps into a continuous spectral space to abstract temporal periodicities. Concurrently, a Spatio-Temporal Co-Gating (STCG) mechanism explicitly filters latent interactions via multiplicative modulation on spatiotemporal contexts.