Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data.
EDBT 2026 Demo / reviewers in the wild / expert

Nichita Diaconu

dblp:241/6157 · DBLP profile ↗
← Back
1ranked-venue papers
1as first author
0since 2021 · last 2019
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Deep learning architectures and training · 50% Transfer learning and domain adaptation · 50%

Topics — the 2 heaviest of 2, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Deep learning architectures and training › equivariant neural network
group equivariant convolution		 0.412019
Learning to Convolve: A Generalized Weight-Tying Approach · ICML 2019
Machine learning › Transfer learning and domain adaptation › structured regularization
weight tying		 0.412019
Learning to Convolve: A Generalized Weight-Tying Approach · ICML 2019

Methods — techniques the papers use, named apart from their topics

filter basis learning · 0.4
YearPublicationVenuePosition
2019 Learning to Convolve: A Generalized Weight-Tying Approach
abstract
Recent work (Cohen & Welling, 2016) has shown that generalizations of convolutions, based on group theory, provide powerful inductive biases for learning. In these generalizations, filters are not only translated but can also be rotated, flipped, etc. However, coming up with exact models of how to rotate a 3x3 filter on a square pixel-grid is difficult. In this paper, we learn how to transform filters for use in the group convolution, focussing on roto-translation. For this, we learn a filter basis and all rotated versions of that filter basis. Filters are then encoded by a set of rotation invariant coefficients. To rotate a filter, we switch the basis. We demonstrate we can produce feature maps with low sensitivity to input rotations, while achieving high performance on MNIST and CIFAR-10.
Nichita Diaconu, Daniel E. Worrall
 ICML1