Irina Higgins

5.4k total citations · 1 hit paper
15 papers, 1.4k citations indexed

About

Irina Higgins is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Cognitive Neuroscience. According to data from OpenAlex, Irina Higgins has authored 15 papers receiving a total of 1.4k indexed citations (citations by other indexed papers that have themselves been cited), including 8 papers in Artificial Intelligence, 6 papers in Computer Vision and Pattern Recognition and 6 papers in Cognitive Neuroscience. Recurrent topics in Irina Higgins's work include Neural dynamics and brain function (3 papers), Generative Adversarial Networks and Image Synthesis (3 papers) and Advanced Memory and Neural Computing (3 papers). Irina Higgins is often cited by papers focused on Neural dynamics and brain function (3 papers), Generative Adversarial Networks and Image Synthesis (3 papers) and Advanced Memory and Neural Computing (3 papers). Irina Higgins collaborates with scholars based in United Kingdom, United States and Canada. Irina Higgins's co-authors include Matthew Botvinick, Alexander Lerchner, Löıc Matthey, Christopher Burgess, Arka Pal, Xavier Glorot, Shakir Mohamed, Demis Hassabis, Le Chang and Doris Y. Tsao and has published in prestigious journals such as Nature Communications, PLoS ONE and Vision Research.

In The Last Decade

Irina Higgins

14 papers receiving 1.3k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework

2017 1.2k citations Irina Higgins, Löıc Matthey et al. International Conference on Learning Representations profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Irina Higgins United Kingdom	8	741	621	146	138	89	15	1.4k
Alexander Lerchner United States	8	711 1.0×	616 1.0×	144 1.0×	160 1.2×	80 0.9×	15	1.4k
Löıc Matthey United States	7	706 1.0×	613 1.0×	144 1.0×	108 0.8×	82 0.9×	11	1.4k
Arka Pal United States	2	681 0.9×	578 0.9×	144 1.0×	68 0.5×	79 0.9×	2	1.2k
Çaǧlar Gülçehre Canada	11	1.0k 1.4×	526 0.8×	188 1.3×	84 0.6×	81 0.9×	26	1.7k
Pascal Lamblin Canada	7	831 1.1×	742 1.2×	282 1.9×	125 0.9×	81 0.9×	9	1.9k
Jyri Kivinen United Kingdom	6	646 0.9×	663 1.1×	125 0.9×	58 0.4×	76 0.9×	8	1.5k
Kyunghyun Cho United States	16	973 1.3×	606 1.0×	191 1.3×	54 0.4×	84 0.9×	39	1.5k
Genevieve Orr United States	8	777 1.0×	550 0.9×	185 1.3×	93 0.7×	98 1.1×	26	1.7k
Kap Luk Chan Singapore	23	546 0.7×	1.1k 1.7×	200 1.4×	139 1.0×	110 1.2×	91	2.0k
Galen Andrew United States	10	1.2k 1.6×	712 1.1×	168 1.2×	92 0.7×	74 0.8×	13	1.9k

Countries citing papers authored by Irina Higgins

Since Specialization

Citations

This map shows the geographic impact of Irina Higgins's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Irina Higgins with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Irina Higgins more than expected).

Fields of papers citing papers by Irina Higgins

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Irina Higgins. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Irina Higgins. The network helps show where Irina Higgins may publish in the future.

Co-authorship network of co-authors of Irina Higgins

This figure shows the co-authorship network connecting the top 25 collaborators of Irina Higgins. A scholar is included among the top collaborators of Irina Higgins based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Irina Higgins. Irina Higgins is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

15 of 15 papers shown

Higgins, Irina, Sébastien Racanière, & Danilo Jimenez Rezende. (2022). Symmetry-Based Representations for Artificial and Biological General Intelligence. Frontiers in Computational Neuroscience. 16. 836498–836498. 14 indexed citations

Higgins, Irina, Le Chang, Demis Hassabis, et al.. (2021). Unsupervised deep learning identifies semantic disentanglement in single inferotemporal face patch neurons. Nature Communications. 12(1). 6456–6456. 74 indexed citations

Higgins, Irina. (2021). Generalizing universal function approximators. Nature Machine Intelligence. 3(3). 192–193. 13 indexed citations

Botev, Aleksandar, Andrew Jaegle, Peter Wirnsberger, Daniel Hennes, & Irina Higgins. (2021). Which priors matter? Benchmarking models for learning latent dynamics. arXiv (Cornell University). 2 indexed citations

Botev, Aleksandar, et al.. (2020). Hamiltonian Generative Networks. International Conference on Learning Representations. 17 indexed citations

Matthey, Löıc, et al.. (2020). Unsupervised Model Selection for Variational Disentangled Representation Learning. International Conference on Learning Representations. 5 indexed citations

Watters, Nicholas, et al.. (2019). A Heuristic for Unsupervised Model Selection for Variational Disentangled Representation Learning.. arXiv (Cornell University). 1 indexed citations

Higgins, Irina, Nicolas Sonnerat, Löıc Matthey, et al.. (2018). SCAN: Learning Hierarchical Compositional Visual Concepts. UCL Discovery (University College London). 17 indexed citations

Achille, Alessandro, Tom Eccles, Löıc Matthey, et al.. (2018). Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies. Neural Information Processing Systems. 31. 9873–9883. 18 indexed citations

10.

Higgins, Irina, Simon M. Stringer, & Jan W. H. Schnupp. (2018). A Computational Account of the Role of Cochlear Nucleus and Inferior Colliculus in Stabilizing Auditory Nerve Firing for Auditory Category Learning. Neural Computation. 30(7). 1801–1829.

11.

Higgins, Irina, Löıc Matthey, Arka Pal, et al.. (2017). beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. International Conference on Learning Representations. 1198 indexed citations breakdown →

12.

Higgins, Irina, Simon M. Stringer, & Jan W. H. Schnupp. (2017). Unsupervised learning of temporal features for word categorization in a spiking neural network model of the auditory brain. PLoS ONE. 12(8). e0180174–e0180174. 8 indexed citations

13.

Ahmad, Nasir, Irina Higgins, Kerry M. M. Walker, & Simon M. Stringer. (2016). Harmonic Training and the Formation of Pitch Representation in a Neural Network Model of the Auditory Brain. Frontiers in Computational Neuroscience. 10. 24–24. 6 indexed citations

14.

Higgins, Irina, et al.. (2012). Learning view invariant recognition with partially occluded objects. Frontiers in Computational Neuroscience. 6. 48–48. 4 indexed citations

15.

Higgins, Irina & Simon M. Stringer. (2011). The role of independent motion in object segmentation in the ventral visual stream: Learning to recognise the separate parts of the body. Vision Research. 51(6). 553–562. 3 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact