Christopher Morris
@chrsmrrs.bsky.social
@RWTH. Previously, @Mila_Quebec, @mcgillu, @polymtl, and @TU_Dortmund. Working on learning with graphs and ML for combinatorial optimization.
In arxiv.org/abs/2412.07106, we leverage modern graph similarity—capturing the fine-grained geometry of MPNNs' feature space—to derive generalization bounds for MPNNs. Our theory is broad, covering various aggregation and loss functions.
March 21, 2025 at 11:11 AM
In arxiv.org/abs/2412.07106, we leverage modern graph similarity—capturing the fine-grained geometry of MPNNs' feature space—to derive generalization bounds for MPNNs. Our theory is broad, covering various aggregation and loss functions.
Want to know about the current understanding of the generalization abilities of GNNs? Please have a look at our survey paper arxiv.org/abs/2503.15650.
Joint work with Antonis Vasileiou, Stefanie Jegelka, and Ron Levie.
Joint work with Antonis Vasileiou, Stefanie Jegelka, and Ron Levie.
March 21, 2025 at 8:05 AM
Want to know about the current understanding of the generalization abilities of GNNs? Please have a look at our survey paper arxiv.org/abs/2503.15650.
Joint work with Antonis Vasileiou, Stefanie Jegelka, and Ron Levie.
Joint work with Antonis Vasileiou, Stefanie Jegelka, and Ron Levie.
Stephan Guennemann kicking off the LOG local meetup in Aachen.
November 27, 2024 at 2:05 PM
Stephan Guennemann kicking off the LOG local meetup in Aachen.