Merge pull request #9 from gabdeo/main

Our submission (2023-11-08-graphs-transformers)
deep-learning-mit · Dec 16, 2023 · 08835e9 · 08835e9
2 parents a1f8e5c + 3161815
commit 08835e9
Show file tree

Hide file tree

Showing 27 changed files with 28,497 additions and 0 deletions.
diff --git a/_posts/2023-11-08-graphs-transformers.md b/_posts/2023-11-08-graphs-transformers.md
diff --git a/assets/bibliography/2023-11-08-graphs-transformers.bib b/assets/bibliography/2023-11-08-graphs-transformers.bib
@@ -12,6 +12,22 @@ @article{DBLP:journals/corr/abs-2112-01898
   bibsource    = {dblp computer science bibliography, https://dblp.org}
 }
 
+@article{DBLP:journals/corr/abs-1905-12712,
+  author       = {Benson Chen and
+                  Regina Barzilay and
+                  Tommi S. Jaakkola},
+  title        = {Path-Augmented Graph Transformer Network},
+  journal      = {CoRR},
+  volume       = {abs/1905.12712},
+  year         = {2019},
+  url          = {http://arxiv.org/abs/1905.12712},
+  eprinttype    = {arXiv},
+  eprint       = {1905.12712},
+  timestamp    = {Mon, 03 Jun 2019 13:42:33 +0200},
+  biburl       = {https://dblp.org/rec/journals/corr/abs-1905-12712.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
 @misc{charton2023transformers,
       title={Can transformers learn the greatest common divisor?}, 
       author={François Charton},
@@ -59,4 +75,107 @@ @article{DBLP:journals/corr/abs-2106-05667
   timestamp    = {Tue, 15 Jun 2021 16:35:15 +0200},
   biburl       = {https://dblp.org/rec/journals/corr/abs-2106-05667.bib},
   bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
+@article{DBLP:journals/corr/abs-1905-13211,
+  author       = {Keyulu Xu and
+                  Jingling Li and
+                  Mozhi Zhang and
+                  Simon S. Du and
+                  Ken{-}ichi Kawarabayashi and
+                  Stefanie Jegelka},
+  title        = {What Can Neural Networks Reason About?},
+  journal      = {CoRR},
+  volume       = {abs/1905.13211},
+  year         = {2019},
+  url          = {http://arxiv.org/abs/1905.13211},
+  eprinttype    = {arXiv},
+  eprint       = {1905.13211},
+  timestamp    = {Mon, 03 Jun 2019 13:42:33 +0200},
+  biburl       = {https://dblp.org/rec/journals/corr/abs-1905-13211.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
+@article{devlin2018bert,
+  title={Bert: Pre-training of deep bidirectional transformers for language understanding},
+  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
+  journal={arXiv preprint arXiv:1810.04805},
+  year={2018}
+}
+
+@article{dosovitskiy2020image,
+  title={An image is worth 16x16 words: Transformers for image recognition at scale},
+  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and others},
+  journal={arXiv preprint arXiv:2010.11929},
+  year={2020}
+}
+
+@inproceedings{wang2020transformer,
+  title={Transformer-based acoustic modeling for hybrid speech recognition},
+  author={Wang, Yongqiang and Mohamed, Abdelrahman and Le, Due and Liu, Chunxi and Xiao, Alex and Mahadeokar, Jay and Huang, Hongzhao and Tjandra, Andros and Zhang, Xiaohui and Zhang, Frank and others},
+  booktitle={ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={6874--6878},
+  year={2020},
+  organization={IEEE}
+}
+
+@article{DBLP:journals/corr/abs-2106-05234,
+  author       = {Chengxuan Ying and
+                  Tianle Cai and
+                  Shengjie Luo and
+                  Shuxin Zheng and
+                  Guolin Ke and
+                  Di He and
+                  Yanming Shen and
+                  Tie{-}Yan Liu},
+  title        = {Do Transformers Really Perform Bad for Graph Representation?},
+  journal      = {CoRR},
+  volume       = {abs/2106.05234},
+  year         = {2021},
+  url          = {https://arxiv.org/abs/2106.05234},
+  eprinttype    = {arXiv},
+  eprint       = {2106.05234},
+  timestamp    = {Fri, 10 Nov 2023 21:09:36 +0100},
+  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-05234.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
+@article{DBLP:journals/corr/VaswaniSPUJGKP17,
+  author       = {Ashish Vaswani and
+                  Noam Shazeer and
+                  Niki Parmar and
+                  Jakob Uszkoreit and
+                  Llion Jones and
+                  Aidan N. Gomez and
+                  Lukasz Kaiser and
+                  Illia Polosukhin},
+  title        = {Attention Is All You Need},
+  journal      = {CoRR},
+  volume       = {abs/1706.03762},
+  year         = {2017},
+  url          = {http://arxiv.org/abs/1706.03762},
+  eprinttype    = {arXiv},
+  eprint       = {1706.03762},
+  timestamp    = {Sat, 23 Jan 2021 01:20:40 +0100},
+  biburl       = {https://dblp.org/rec/journals/corr/VaswaniSPUJGKP17.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
+
+@article{dudzik2022graph,
+  title={Graph neural networks are dynamic programmers},
+  author={Dudzik, Andrew J and Veli{\v{c}}kovi{\'c}, Petar},
+  journal={Advances in Neural Information Processing Systems},
+  volume={35},
+  pages={20635--20647},
+  year={2022}
+}
+
+
+@inproceedings{li2023transformers,
+  title={Transformers as algorithms: Generalization and stability in in-context learning},
+  author={Li, Yingcong and Ildiz, Muhammed Emrullah and Papailiopoulos, Dimitris and Oymak, Samet},
+  booktitle={International Conference on Machine Learning},
+  pages={19565--19594},
+  year={2023},
+  organization={PMLR}
 }