{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"1905.11136","title":"Provably Powerful Graph Networks","created":"2019-05-27","cited_by_count":389},{"id":"2006.09252","title":"Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting","created":"2020-06-16","cited_by_count":313},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"id":"2002.04025","title":"Can Graph Neural Networks Count Substructures?","created":"2020-02-10","cited_by_count":236},{"id":"2103.03212","title":"Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks","created":"2021-03-04","cited_by_count":221},{"id":"2106.12575","title":"Weisfeiler and Lehman Go Cellular: CW Networks","created":"2021-06-23","cited_by_count":218},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2110.02910","title":"Equivariant Subgraph Aggregation Networks","created":"2021-10-06","cited_by_count":154},{"id":"2202.05441","title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","created":"2022-02-11","cited_by_count":144},{"id":"2010.08853","title":"From Local Structures to Size Generalization in Graph Neural Networks","created":"2020-10-17","cited_by_count":124},{"id":"2112.09992","title":"Weisfeiler and Leman go Machine Learning: The Story so far","created":"2021-12-18","cited_by_count":122},{"id":"1511.08228","title":"Neural GPUs Learn Algorithms","created":"2015-11-25","cited_by_count":121},{"id":"1910.10593","title":"Neural Execution of Graph Algorithms","created":"2019-10-23","cited_by_count":121},{"id":"2006.10643","title":"Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs","created":"2020-06-18","cited_by_count":115},{"id":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106},{"id":"2206.04301","title":"Unveiling Transformers with LEGO: a synthetic reasoning task","created":"2022-06-09","cited_by_count":106},{"id":"2006.07054","title":"Learning the Travelling Salesperson Problem Requires Rethinking Generalization","created":"2020-06-12","cited_by_count":98},{"id":"2105.02761","title":"Neural Algorithmic Reasoning","created":"2021-05-06","cited_by_count":94},{"id":"2103.05045","title":"Size-Invariant Graph Representations for Graph Classification Extrapolations","created":"2021-03-08","cited_by_count":84},{"id":"2103.03012","title":"The Transformer Network for the Traveling Salesman Problem","created":"2021-03-04","cited_by_count":59},{"id":"2202.00645","title":"Generalization Analysis of Message Passing Neural Networks on Large Random Graphs","created":"2022-02-01","cited_by_count":59},{"id":"2209.11142","title":"A Generalist Neural Algorithmic Learner","created":"2022-09-22","cited_by_count":59},{"id":"2206.11168","title":"Ordered Subgraph Aggregation Networks","created":"2022-06-22","cited_by_count":57},{"id":"2006.06380","title":"Pointer Graph Networks","created":"2020-06-11","cited_by_count":53},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53},{"id":"1912.06058","title":"Coloring graph neural networks for node disambiguation","created":"2019-12-12","cited_by_count":52},{"id":"2006.08084","title":"Neural Execution Engines: Learning to Execute Subroutines","created":"2020-06-15","cited_by_count":36},{"id":"2109.07276","title":"Sequence Length is a Domain: Length-based Overfitting in Transformer Models","created":"2021-09-15","cited_by_count":35},{"id":"2002.09398","title":"It's Not What Machines Can Learn, It's What We Cannot Teach","created":"2020-02-21","cited_by_count":29},{"id":"2107.12580","title":"Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization","created":"2021-07-27","cited_by_count":29},{"id":"2205.13647","title":"Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures","created":"2022-05-26","cited_by_count":17},{"id":"2007.03629","title":"Strong Generalization and Efficiency in Neural Programs","created":"2020-07-07","cited_by_count":12},{"id":"1904.01543","title":"Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings","created":"2019-04-02","cited_by_count":9},{"id":"2010.13547","title":"Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks","created":"2020-10-26","cited_by_count":6},{"id":"2202.08833","title":"What Functions Can Graph Neural Networks Generate?","created":"2022-02-17","cited_by_count":5}],"next_cursor":null}