{"total":20,"rows":[{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133,"area":null},{"id":"2306.06529","title":"Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem","created":"2023-06-10","cited_by_count":34,"area":null},{"id":"2301.11039","title":"WL meet VC","created":"2023-01-26","cited_by_count":31,"area":null},{"id":"2303.04613","title":"The Descriptive Complexity of Graph Neural Networks","created":"2023-03-08","cited_by_count":26,"area":null},{"id":"2306.03698","title":"Fine-grained Expressivity of Graph Neural Networks","created":"2023-06-06","cited_by_count":25,"area":null},{"id":"2402.07568","title":"Weisfeiler-Leman at the margin: When more expressivity matters","created":"2024-02-12","cited_by_count":13,"area":null},{"id":"2301.13821","title":"Complete Neural Networks for Complete Euclidean Graphs","created":"2023-01-31","cited_by_count":10,"area":null},{"id":"2307.04661","title":"On the power of graph neural networks and the role of the activation function","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2410.09118","title":"FSW-GNN: A Bi-Lipschitz WL-Equivalent Graph Neural Network","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2402.03966","title":"On dimensionality of feature vectors in MPNNs","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2407.02025","title":"On the Expressive Power of Sparse Geometric MPNNs","created":"2024-07-02","cited_by_count":7,"area":null},{"id":"2402.02287","title":"Future Directions in the Theory of Graph Machine Learning","created":"2024-02-03","cited_by_count":6,"area":null},{"id":"2505.09361","title":"Efficient Mixed Precision Quantization in Graph Neural Networks","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2410.07829","title":"A note on the VC dimension of 1-dimensional GNNs","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2310.13139","title":"The logic of rational graph neural networks","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2311.01205","title":"Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2510.13615","title":"Message Passing on the Edge: Towards Scalable and Expressive GNNs","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2603.03963","title":"TFWaveFormer: Temporal-Frequency Collaborative Multi-level Wavelet Transformer for Dynamic Link Prediction","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.14846","title":"Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2610.16993","title":"Constant-Depth Rational-Weight GNNs and their Connection to Schanuel's Conjecture","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}