{"list":"other","total":53,"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":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"1905.07953","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","created":"2019-05-20","cited_by_count":541},{"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":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"1911.05485","title":"Diffusion Improves Graph Learning","created":"2019-10-28","cited_by_count":414},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","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":"2110.14446","title":"Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods","created":"2021-10-27","cited_by_count":311},{"id":"1905.09550","title":"Revisiting Graph Neural Networks: All We Have is Low-Pass Filters","created":"2019-05-23","cited_by_count":261},{"id":"2106.12575","title":"Weisfeiler and Lehman Go Cellular: CW Networks","created":"2021-06-23","cited_by_count":218},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2201.08821","title":"Representing Long-Range Context for Graph Neural Networks with Global Attention","created":"2022-01-21","cited_by_count":195},{"id":"2302.02941","title":"On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology","created":"2023-02-06","cited_by_count":166},{"id":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153},{"id":"1903.02541","title":"Relational Pooling for Graph Representations","created":"2019-03-06","cited_by_count":150},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112},{"id":"2210.11790","title":"FoSR: First-order spectral rewiring for addressing oversquashing in GNNs","created":"2022-10-21","cited_by_count":105},{"id":"2106.04319","title":"Breaking the Limits of Message Passing Graph Neural Networks","created":"2021-06-08","cited_by_count":101},{"id":"2302.06835","title":"Understanding Oversquashing in GNNs through the Lens of Effective Resistance","created":"2023-02-14","cited_by_count":97},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2301.09474","title":"DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion","created":"2023-01-23","cited_by_count":87},{"id":"2403.01232","title":"Polynormer: Polynomial-Expressive Graph Transformer in Linear Time","created":"2024-03-02","cited_by_count":65},{"id":"2302.07090","title":"A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests","created":"2023-02-14","cited_by_count":64},{"id":"2310.01668","title":"Locality-Aware Graph-Rewiring in GNNs","created":"2023-10-02","cited_by_count":56},{"id":"2102.01350","title":"Graph Coarsening with Neural Networks","created":"2021-02-02","cited_by_count":55},{"id":"2211.14208","title":"GREAD: Graph Neural Reaction-Diffusion Networks","created":"2022-11-25","cited_by_count":54},{"id":"2102.08786","title":"Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing","created":"2021-02-17","cited_by_count":47},{"id":"2311.07073","title":"Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges","created":"2023-11-13","cited_by_count":22},{"id":"2108.06208","title":"LT-OCF: Learnable-Time ODE-based Collaborative Filtering","created":"2021-08-08","cited_by_count":21},{"id":"2405.11951","title":"Distinguished In Uniform: Self Attention Vs. Virtual Nodes","created":"2024-05-20","cited_by_count":20},{"id":"2305.02866","title":"Hierarchical Transformer for Scalable Graph Learning","created":"2023-05-04","cited_by_count":17},{"id":"2405.13526","title":"Understanding Virtual Nodes: Oversquashing and Node Heterogeneity","created":"2024-05-22","cited_by_count":14},{"id":"2312.04234","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","created":"2023-12-07","cited_by_count":11},{"id":"2406.03671","title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","created":"2024-06-06","cited_by_count":10},{"id":"2211.14425","title":"PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations","created":"2022-11-26","cited_by_count":8},{"id":"2406.12059","title":"A Scalable and Effective Alternative to Graph Transformers","created":"2024-06-17","cited_by_count":4},{"id":"2212.03120","title":"Towards a Better Understanding of the Characteristics of Fractal Networks","created":"2022-12-06","cited_by_count":2}],"next_cursor":null}