--- title: "Peter Battaglia — author profile and papers" description: "Peter Battaglia, Google DeepMind: 2 papers on Elamur Research (2017–2018), h-index 47 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/peter-battaglia/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/peter-battaglia/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Peter Battaglia # Peter Battaglia Peter Battaglia's papers here concern relational reasoning in neural networks. They ask how deep learning systems can represent entities and the relations among them, and so generalize by recombining familiar parts into new inferences and actions. Both works ask which structural assumptions should be built into an architecture rather than left to be learned from scratch, and both belong to the topic of [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/). The more cited of the two, [Relational inductive biases, deep learning, and graph networks](https://md.research.elamur.ai/free/en/papers/battaglia-2018-relational-inductive-biases-deep-learning/) (2018), is a position paper and literature review with no new experiments. It argues that hand-built structure and end-to-end learning need not be treated as rivals. It then gathers a range of earlier approaches into a single graph network framework grounded in relational inductive biases. The earlier [A simple neural network module for relational reasoning](https://md.research.elamur.ai/free/en/papers/santoro-2017-simple-neural-network-module-relational/) (2017) introduced the Relation Network, a small add-on component. It applies one shared function to every pair of input objects, adds up the outcomes, and feeds that total into a second network. The objects can be cells of a convolutional feature map, encoded sentences, or rows of a state description. Taken in order, the two papers move from a single pairwise module toward a general framework for computation over graphs. Battaglia's current affiliation is [Google DeepMind](https://md.research.elamur.ai/free/en/companies/google-deepmind/) in London. Earlier bylines include the [Massachusetts Institute of Technology](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/), [Google](https://md.research.elamur.ai/free/en/companies/google/) in Mountain View and the [University of Minnesota](https://md.research.elamur.ai/free/en/universities/university-of-minnesota/). [Adam Santoro](https://md.research.elamur.ai/free/en/authors/adam-santoro/), [David Raposo](https://md.research.elamur.ai/free/en/authors/david-raposo/) and [Mateusz Malinowski](https://md.research.elamur.ai/free/en/authors/mateusz-malinowski/) appear as co-authors on both papers here. Other collaborators include [Timothy Lillicrap](https://md.research.elamur.ai/free/en/authors/timothy-lillicrap/), Caglar Gulcehre and Francis Song. Peter Battaglia has 2 papers in our library, in 2017–2018, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Adam Santoro](https://md.research.elamur.ai/free/en/authors/adam-santoro/), [David Raposo](https://md.research.elamur.ai/free/en/authors/david-raposo/), [Mateusz Malinowski](https://md.research.elamur.ai/free/en/authors/mateusz-malinowski/). 2 papers in our library · 2017–2018 [OpenAlex](https://openalex.org/A5059792149) · [ORCID](https://orcid.org/0000-0003-3622-7111) · [Wikidata](https://www.wikidata.org/wiki/Q125890184) · [**h-index 47**](https://openalex.org/authors/A5059792149) · [114 works](https://openalex.org/works?filter=author.id:A5059792149) · [10,289 citations](https://openalex.org/works?filter=author.id:A5059792149&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/peter-battaglia/#papers) · [🔗 330 citations in our library](https://md.research.elamur.ai/free/en/authors/peter-battaglia/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Star rank #878](https://md.research.elamur.ai/free/en/paper-stars/page/9/#star-878) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Peter+Battaglia) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Peter+Battaglia) · [dblp](https://dblp.org/search?q=Peter+Battaglia) · [ACL Anthology](https://aclanthology.org/search/?q=Peter+Battaglia) ## Affiliations [🏢**Google DeepMind** London · United Kingdom 2016–2026 · 27 papers*current*](https://md.research.elamur.ai/free/en/companies/google-deepmind/) · [🎓**Massachusetts Institute of Technology** Cambridge · United States 2010–2023 · 27 papers](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) · [🏢**Google** Mountain View · United States 2017–2020 · 13 papers](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**University of Minnesota** Minneapolis · United States 2003–2010 · 6 papers](https://md.research.elamur.ai/free/en/universities/university-of-minnesota/) · [🏢**Google** London · United Kingdom 2016–2025 · 4 papers](https://md.research.elamur.ai/free/en/companies/google-united-kingdom/) · [🎓**University of Rochester** Rochester · United States 2003 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-rochester/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed. ## Topics [Reasoning (1)](https://md.research.elamur.ai/free/en/topics/reasoning/) ## Works by year ### 2010s [**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/battaglia-2018-relational-inductive-biases-deep-learning/) · [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/santoro-2017-simple-neural-network-module-relational/) ## Papers The most cited first (OpenAlex and our library). 1. **[Relational inductive biases, deep learning, and graph networks](https://md.research.elamur.ai/free/en/papers/battaglia-2018-relational-inductive-biases-deep-learning/)** *(2018 · 2,285 citations)* Authors from DeepMind, Google Brain, MIT and the University of Edinburgh consider how to teach artificial intelligence systems combinatorial generalization. 2. **[A simple neural network module for relational reasoning](https://md.research.elamur.ai/free/en/papers/santoro-2017-simple-neural-network-module-relational/)** *(2017 · 590 citations)* Neural networks such as CNNs and MLPs often fail at questions that depend on how entities relate to each other, rather than on the properties of single entities. ## Also in our library 2 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 6 co-authors with a page, the most papers together first. - [Adam Santoro](https://md.research.elamur.ai/free/en/authors/adam-santoro/) ×2 - [David Raposo](https://md.research.elamur.ai/free/en/authors/david-raposo/) ×2 - [Mateusz Malinowski](https://md.research.elamur.ai/free/en/authors/mateusz-malinowski/) ×2 - [Caglar Gulcehre](https://md.research.elamur.ai/free/en/authors/caglar-gulcehre/) - [Francis Song](https://md.research.elamur.ai/free/en/authors/francis-song/) - [Timothy Lillicrap](https://md.research.elamur.ai/free/en/authors/timothy-lillicrap/) ## Cited by Papers of our library cite their works 330 times (of the 140,884 papers whose bibliographies we read); [23 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/peter-battaglia/cited-by/).