{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"1704.01665","title":"Learning Combinatorial Optimization Algorithms over Graphs","created":"2017-04-05","cited_by_count":561},{"id":"2006.10637","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","created":"2020-06-18","cited_by_count":530},{"id":"2011.02260","title":"Graph Neural Networks in Recommender Systems: A Survey","created":"2020-11-04","cited_by_count":494},{"id":"2004.05718","title":"Principal Neighbourhood Aggregation for Graph Nets","created":"2020-04-12","cited_by_count":478},{"id":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"1809.07426","title":"Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding","created":"2018-09-19","cited_by_count":476},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"id":"2002.07962","title":"Inductive Representation Learning on Temporal Graphs","created":"2020-02-19","cited_by_count":462},{"id":"1812.04202","title":"Deep Learning on Graphs: A Survey","created":"2018-12-11","cited_by_count":393},{"id":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","cited_by_count":346},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"1905.11485","title":"Representation Learning for Dynamic Graphs: A Survey","created":"2019-05-27","cited_by_count":265},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"1711.04725","title":"Neural Attentive Session-based Recommendation","created":"2017-11-13","cited_by_count":237},{"id":"1606.03126","title":"Key-Value Memory Networks for Directly Reading Documents","created":"2016-06-09","cited_by_count":223},{"id":"2002.06157","title":"Generalization and Representational Limits of Graph Neural Networks","created":"2020-02-14","cited_by_count":218},{"id":"1906.04817","title":"Position-aware Graph Neural Networks","created":"2019-06-11","cited_by_count":203},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"1611.08108","title":"Dynamic Key-Value Memory Networks for Knowledge Tracing","created":"2016-11-24","cited_by_count":171},{"id":"1703.01988","title":"Neural Episodic Control","created":"2017-03-06","cited_by_count":151},{"id":"1903.02541","title":"Relational Pooling for Graph Representations","created":"2019-03-06","cited_by_count":150},{"id":"1506.02075","title":"Large-scale Simple Question Answering with Memory Networks","created":"2015-06-05","cited_by_count":127},{"id":"2009.06211","title":"Implicit Graph Neural Networks","created":"2020-09-14","cited_by_count":100},{"id":"1909.04063","title":"Exploratory Combinatorial Optimization with Reinforcement Learning","created":"2019-09-09","cited_by_count":82},{"id":"1806.01822","title":"Relational recurrent neural networks","created":"2018-06-05","cited_by_count":65},{"id":"2004.08500","title":"A Formal Hierarchy of RNN Architectures","created":"2020-04-18","cited_by_count":62},{"id":"2002.09518","title":"Memory-Based Graph Networks","created":"2020-02-21","cited_by_count":56},{"id":"1912.11730","title":"Memory Augmented Graph Neural Networks for Sequential Recommendation","created":"2019-12-26","cited_by_count":46},{"id":"1806.07243","title":"Learning Conditioned Graph Structures for Interpretable Visual Question Answering","created":"2018-06-19","cited_by_count":45},{"id":"1905.13732","title":"End to end learning and optimization on graphs","created":"2019-05-31","cited_by_count":44},{"id":"1910.13406","title":"Generalization of Reinforcement Learners with Working and Episodic Memory","created":"2019-10-29","cited_by_count":36},{"id":"2002.03519","title":"Self-Attentive Associative Memory","created":"2020-02-10","cited_by_count":33},{"id":"2111.05498","title":"Attention Approximates Sparse Distributed Memory","created":"2021-11-10","cited_by_count":29},{"id":"1611.09913","title":"Capacity and Trainability in Recurrent Neural Networks","created":"2016-11-29","cited_by_count":28},{"id":"1904.05582","title":"Recurrent Space-time Graph Neural Networks","created":"2019-04-11","cited_by_count":19},{"id":"1912.11615","title":"Deep Graph Similarity Learning: A Survey","created":"2019-12-25","cited_by_count":19},{"id":"1810.08163","title":"Fast deep reinforcement learning using online adjustments from the past","created":"2018-10-18","cited_by_count":14},{"id":"2103.01043","title":"Persistent Message Passing","created":"2021-03-01","cited_by_count":13},{"id":"1805.03716","title":"Long Short-Term Memory as a Dynamically Computed Element-wise Weighted Sum","created":"2018-05-09","cited_by_count":4}],"next_cursor":null}