Updated AAS constant publication info

Author: SamAdamDay

_bibliography/papers.bib

@@ -15,17 +15,18 @@ @misc{hammond-adam-day-2024-nip
   preview       = {nip-schematic.png},
 }
 
-@misc{adam-day-et-al-2024-aas-constant,
+@inproceedings{adam-day-et-al-2024-aas-constant,
   author        = {Sam Adam-Day and Michael Benedikt and İsmail İlkan Ceylan and Ben Finkelshtein},
-  note          = {To appear in NeurIPS '24},
-  howpublished  = {Preprint},
+  booktitle     = {Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS)},
   title         = {Almost Surely Asymptotically Constant Graph Neural Networks},
   year          = {2024},
   bibtex_show   = {true},
   eprint        = {2403.03880},
   archiveprefix = {arXiv},
   primaryclass  = {cs.LG},
   arxiv         = {2403.03880},
+  url           = {https://openreview.net/forum?id=Dn68qdfTry},
+  html          = {https://openreview.net/forum?id=Dn68qdfTry},
   abstract      = {Graph neural networks (GNNs) are the predominant architectures for a variety of learning tasks on graphs. We present a new angle on the expressive power of GNNs by studying how the predictions of a GNN probabilistic classifier evolve as we apply it on larger graphs drawn from some random graph model. We show that the output converges to a constant function, which upper-bounds what these classifiers can express uniformly. This convergence phenomenon applies to a very wide class of GNNs, including state of the art models, with aggregates including mean and the attention-based mechanism of graph transformers. Our results apply to a broad class of random graph models, including the (sparse) Erdős-Rényi model and the stochastic block model. We empirically validate these findings, observing that the convergence phenomenon already manifests itself on graphs of relatively modest size.},
   preview       = {aas-constant-schematic.png},
   selected      = {true}