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.
This map shows the geographic impact of Andriy Mnih'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 Andriy Mnih with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Andriy Mnih more than expected).
This network shows the impact of papers produced by Andriy Mnih. 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 Andriy Mnih. The network helps show where Andriy Mnih may publish in the future.
Co-authorship network of co-authors of Andriy Mnih
This figure shows the co-authorship network connecting the top 25 collaborators of Andriy Mnih.
A scholar is included among the top collaborators of Andriy Mnih 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 Andriy Mnih. Andriy Mnih is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Kim, Hyunjik, George Papamakarios, & Andriy Mnih. (2021). The Lipschitz Constant of Self-Attention. International Conference on Machine Learning. 5562–5571.1 indexed citations
2.
Dong, Zhe, Andriy Mnih, & George Tucker. (2020). DisARM: An Antithetic Gradient Estimator for Binary Latent Variables. Neural Information Processing Systems. 33. 18637–18647.
3.
Kim, Hyunjik & Andriy Mnih. (2018). Disentangling by Factorising. International Conference on Machine Learning. 2649–2658.93 indexed citations
4.
Mohamed, Shakir, et al.. (2018). Implicit Reparameterization Gradients. Neural Information Processing Systems. 31. 441–452.16 indexed citations
5.
Bornschein, Jörg, Andriy Mnih, Daniel Zoran, & Danilo Jimenez Rezende. (2017). Variational Memory Addressing in Generative Models. Neural Information Processing Systems. 30. 3920–3929.4 indexed citations
Mnih, Andriy & Danilo Jimenez Rezende. (2016). Variational inference for Monte Carlo objectives. International Conference on Machine Learning. 2188–2196.31 indexed citations
8.
Mnih, Andriy & Koray Kavukcuoglu. (2013). Learning word embeddings efficiently with noise-contrastive estimation. Neural Information Processing Systems. 26. 2265–2273.262 indexed citations
9.
Mnih, Andriy & Yee Whye Teh. (2012). Learning Label Trees for Probabilistic Modelling of Implicit Feedback. Neural Information Processing Systems. 25. 2816–2824.6 indexed citations
Mnih, Andriy. (2011). Taxonomy-informed latent factor models for implicit feedback. UCL Discovery (University College London). 169–181.10 indexed citations
12.
Zhang, Yuecheng, Andriy Mnih, & Geoffrey E. Hinton. (2008). Improving a statistical language model by modulating the effects of context words. The European Symposium on Artificial Neural Networks. 493–498.1 indexed citations
Salakhutdinov, Ruslan & Andriy Mnih. (2008). Bayesian probabilistic matrix factorization using Markov chain Monte Carlo. 880–887.974 indexed citations breakdown →
15.
Sutskever, Ilya, et al.. (2007). Visualizing Similarity Data with a Mixture of Maps. UCL Discovery (University College London). 67–74.45 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.