Alert button
Picture for Vladislav Polianskii

Vladislav Polianskii

Alert button

Active Nearest Neighbor Regression Through Delaunay Refinement

Jun 16, 2022
Alexander Kravberg, Giovanni Luca Marchetti, Vladislav Polianskii, Anastasiia Varava, Florian T. Pokorny, Danica Kragic

Figure 1 for Active Nearest Neighbor Regression Through Delaunay Refinement
Figure 2 for Active Nearest Neighbor Regression Through Delaunay Refinement
Figure 3 for Active Nearest Neighbor Regression Through Delaunay Refinement
Figure 4 for Active Nearest Neighbor Regression Through Delaunay Refinement

We introduce an algorithm for active function approximation based on nearest neighbor regression. Our Active Nearest Neighbor Regressor (ANNR) relies on the Voronoi-Delaunay framework from computational geometry to subdivide the space into cells with constant estimated function value and select novel query points in a way that takes the geometry of the function graph into account. We consider the recent state-of-the-art active function approximator called DEFER, which is based on incremental rectangular partitioning of the space, as the main baseline. The ANNR addresses a number of limitations that arise from the space subdivision strategy used in DEFER. We provide a computationally efficient implementation of our method, as well as theoretical halting guarantees. Empirical results show that ANNR outperforms the baseline for both closed-form functions and real-world examples, such as gravitational wave parameter inference and exploration of the latent space of a generative model.

* Accepted at the International Conference on Machine Learning (ICML) 2022 
Viaarxiv icon

Delaunay Component Analysis for Evaluation of Data Representations

Feb 14, 2022
Petra Poklukar, Vladislav Polianskii, Anastasia Varava, Florian Pokorny, Danica Kragic

Figure 1 for Delaunay Component Analysis for Evaluation of Data Representations
Figure 2 for Delaunay Component Analysis for Evaluation of Data Representations
Figure 3 for Delaunay Component Analysis for Evaluation of Data Representations
Figure 4 for Delaunay Component Analysis for Evaluation of Data Representations

Advanced representation learning techniques require reliable and general evaluation methods. Recently, several algorithms based on the common idea of geometric and topological analysis of a manifold approximated from the learned data representations have been proposed. In this work, we introduce Delaunay Component Analysis (DCA) - an evaluation algorithm which approximates the data manifold using a more suitable neighbourhood graph called Delaunay graph. This provides a reliable manifold estimation even for challenging geometric arrangements of representations such as clusters with varying shape and density as well as outliers, which is where existing methods often fail. Furthermore, we exploit the nature of Delaunay graphs and introduce a framework for assessing the quality of individual novel data representations. We experimentally validate the proposed DCA method on representations obtained from neural networks trained with contrastive objective, supervised and generative models, and demonstrate various use cases of our extended single point evaluation framework.

* ICLR 2022 camera ready 
Viaarxiv icon