Yixuan He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yixuan He has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Aaron A. Sandel
Department of Anthropology, University of Texas at Austin, Austin, TX, USA
1 shared publication Alfred Tumusiime
Ngogo Chimpanzee Project, Fort Portal, Uganda
1 shared publication- Amal Gueroudji
Argonne National Laboratory
1 shared publication - Bas van Boekholt
Institute of Cognitive Science, University of Osnabrück, Osnabrück, Germany
1 shared publication - Blessing A. Apamaku
Department of Anthropology, University of Texas at Austin, Austin, TX, USA
1 shared publication Brian Kamugyisha
Ngogo Chimpanzee Project, Fort Portal, Uganda
1 shared publication
Latest Publications
- Top Cited Papers
- 9 April 2026
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 392 (6794) , 216-220
Lethal conflict after group fission in wild chimpanzees
Territorial conflicts in animals can inform aspects of human warfare, but civil war, with its shifting group identities, has not been previously observed. We report a rare, permanent fission in the largest-known group of wild chimpanzees ( Pan troglodytes ). Using 30 years of behavioral observations and network analyses, we describe a transition from cohesion to polarization in 2015 and the emergence of two distinct groups by 2018. Over the next 7 years, members of one group made 24 attacks, killing at least seven mature males and 17 infants in the other group. These findings indicate that group identities can shift and escalate into lethal hostility in one of our closest living relatives in the absence of the cultural markers often thought necessary for human warfare.
- 9 April 2026
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 392 (6794) , 216-220
Top Cited PapersLethal conflict after group fission in wild chimpanzees
Territorial conflicts in animals can inform aspects of human warfare, but civil war, with its shifting group identities, has not been previously observed. We report a rare, permanent fission in the largest-known group of wild chimpanzees ( Pan troglodytes ). Using 30 years of behavioral observations and network analyses, we describe a transition from cohesion to polarization in 2015 and the emergence of two distinct groups by 2018. Over the next 7 years, members of one group made 24 attacks, killing at least seven mature males and 17 infants in the other group. These findings indicate that group identities can shift and escalate into lethal hostility in one of our closest living relatives in the absence of the cultural markers often thought necessary for human warfare.
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 217-236
PGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 217-236
Open AccessPGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 518-530
Pyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations
Spectral methods for graph neural networks (GNNs) have achieved great success. Despite their success, many works have shown that existing approaches are mainly focused on low-frequency information which may not be pertinent to the task at hand. Recent efforts have been made to design new graph filters for wider frequency profiles, but it remains an open problem how to learn multi-scale disentangled node embeddings in the graph Fourier domain. In this paper, we propose a graph (signal) sampling and filtering framework, entitled Pyramid Graph Neural Network (PyGNN), which follows the Downsampling-Filtering-Upsampling-Decoding scheme. To be specific, we develop an ω-bandlimited downsampling approach to split input graph into subgraphs for the reduction of high-frequency components, then perform spectral graph filters on subgraphs to achieve node embeddings with different frequency bands, and propose a Laplacian smoothing-based upsampling approach to extrapolate the node embedding on subgraphs to the full set of vertices on the original graph. In the end, we add frequency-aware gated units to decode node embeddings of different frequencies for downstream tasks. Results on both homophilic and heterophilic graph datasets show its superiority over state-of-the-art methods.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 518-530
Open AccessPyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations
Spectral methods for graph neural networks (GNNs) have achieved great success. Despite their success, many works have shown that existing approaches are mainly focused on low-frequency information which may not be pertinent to the task at hand. Recent efforts have been made to design new graph filters for wider frequency profiles, but it remains an open problem how to learn multi-scale disentangled node embeddings in the graph Fourier domain. In this paper, we propose a graph (signal) sampling and filtering framework, entitled Pyramid Graph Neural Network (PyGNN), which follows the Downsampling-Filtering-Upsampling-Decoding scheme. To be specific, we develop an ω-bandlimited downsampling approach to split input graph into subgraphs for the reduction of high-frequency components, then perform spectral graph filters on subgraphs to achieve node embeddings with different frequency bands, and propose a Laplacian smoothing-based upsampling approach to extrapolate the node embedding on subgraphs to the full set of vertices on the original graph. In the end, we add frequency-aware gated units to decode node embeddings of different frequencies for downstream tasks. Results on both homophilic and heterophilic graph datasets show its superiority over state-of-the-art methods.