Here we will compile all of the references to books, theses, papers, talks and code that we found useful while preparing or conducting the tutorial.
Books
- Cormen, TH., Leiserson, CE., Rivest, RL. and Stein, C. Introduction to Algorithms. MIT Press
- Bellman, RE. Dynamic Programming. Princeton University Press
Papers
- Harris, TE. and Ross, FS. Fundamentals of a Method for Evaluating Rail Net Capacities. Project RAND Research Memorandum
- Vlastelica, M., Paulus, A., Musil, V., Martius, G. and Rolínek, M. Differentiation of Blackbox Combinatorial Solvers. ICLR’20
- Hamrick, JB., Allen, KR., Bapst, V., Zhu, T., McKee, KR., Tenenbaum, JB. and Battaglia, PW. Relational inductive bias for physical construction in humans and machines. CogSci’18
- Xu, K., Li, J., Zhang, M., Du, SS., Kawarabayashi, K-I. and Jegelka, S. What Can Neural Networks Reason About?. ICLR’20
- Xu, K., Zhang, M., Li, J., Du, SS., Kawarabayashi, K-I. and Jegelka, S. How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks. ICLR’21
- Bevilacqua, B., Zhou, Y. and Ribeiro, B. Size-Invariant Graph Representations for Graph Classification Extrapolations. ICML’21
- Fereydounian, M., Hassani, H. and Karbasi, A. What Functions Can Graph Neural Networks Generate?. arXiv’22
- Freivalds, K., Ozoliņš, E. and Šostaks, A. Neural Shuffle-Exchange Networks - Sequence Processing in O(n log n) Time. NeurIPS’19
- Veličković, P., Ying, R., Padovano, M., Hadsell, R. and Blundell, C. Neural Execution of Graph Algorithms. ICLR’20
- Shanahan, M., Nikiforou, K., Creswell, A., Kaplanis, C., Barrett, D. and Garnelo, M. An Explicitly Relational Neural Network Architecture. ICML’20
- Tang, H., Huang, Z., Gu, J., Lu, B-L. and Su, H. Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs. NeurIPS’20
- Veličković, P., Buesing, L., Overlan, MC., Pascanu, R., Vinyals, O. and Blundell, C. Pointer Graph Networks. NeurIPS’20
- Strathmann, H., Barekatain, M., Blundell, C. and Veličković, P. Persistent Message Passing. ICLR’21 SimDL
- Karalias, N. and Loukas, A. Erdős Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs. NeurIPS’20
- Yehudai, G., Fetaya, E., Meirom, E., Chechik, G. and Maron, H. From Local Structures to Size Generalization in Graph Neural Networks. ICML’21
- Buffelli, D., Liò, P. and Vandin, F. SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks. NeurIPS’22
- Bansal, A., Schwarzschild, A., Borgnia, E., Emam, Z., Huang, F., Goldblum, M. and Goldstein, T. End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking. NeurIPS’22
- Xhonneux, L-PAC., Deac, A., Veličković, P. and Tang, J. How to transfer algorithmic reasoning knowledge to learn new algorithms?. NeurIPS’21
- Ibarz, B., Kurin, V., Papamakarios, G., Nikiforou, K., Bennani, M., Csordás, R., Dudzik, A., Bošnjak, M., Vitvitskyi, A., Rubanova, Y., Deac, A., Bevilacqua, B., Ganin, Y., Blundell, C. and Veličković, P. A Generalist Neural Algorithmic Learner. LoG’22
- Veličković, P., Badia, AP., Budden, D., Pascanu, R., Banino, A., Dashevskiy, M., Hadsell, R. and Blundell, C. The CLRS Algorithmic Reasoning Benchmark. ICML’22
- Deac, A., Bacon, P-L. and Tang, J. Graph neural induction of value iteration. ICML’20 GRL+
- Deac, A., Veličković, P., Milinković, O., Bacon, P-L., Tang, J. and Nikolić, M. Neural Algorithmic Reasoners are Implicit Planners. NeurIPS’21
- Veličković, P. and Blundell, C. Neural Algorithmic Reasoning. Patterns’21
- Silver, D., Huang, A., Maddison, CJ., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T. and Hassabis, D. Mastering the game of Go with deep neural networks and tree search. Nature’16
- Segler, MHS., Preuss, M. and Waller, MP. Planning chemical syntheses with deep neural networks and symbolic AI. Nature’18
- Tamar, A., Wu, Y., Thomas, G., Levine, S. and Abbeel, P. Value Iteration Networks. NeurIPS’16
- Niu, S., Chen, S., Guo, H., Targonski, C., Smith, M. and Kovačević, J. Generalized Value Iteration Networks:Life Beyond Lattices. AAAI’18
- Kipf, T., van der Pol, E. and Welling, M. Contrastive Learning of Structured World Models. ICLR’20
- Farquhar, G., Rocktäschel, T., Igl, M. and Whiteson, S. TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning. ICLR’18
- Oh, J., Singh, S. and Lee, H. Value Prediction Networks. NeurIPS’17
- He, Y., Veličković, P., Liò, P. and Deac, A. Continuous Neural Algorithmic Planners. LoG’22
- Veličković, P., Bošnjak, M., Kipf, T., Lerchner, A., Hadsell, R., Pascanu, R. and Blundell, C. Reasoning-Modulated Representations. LoG’22
- Dudzik, A. and Veličković, P. Graph Neural Networks are Dynamic Programmers. NeurIPS’22
- Bellman, R. On a Routing Problem. Quart. Appl. Math.’58
- Dudzik, A. Quantales and Hyperstructures: Monads, Mo’ Problems. PhD Thesis
- Ong, E. and Veličković, P. Learnable Commutative Monoids for Graph Neural Networks. LoG’22