{"list":"other","total":67,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"1905.11136","title":"Provably Powerful Graph Networks","created":"2019-05-27","cited_by_count":389},{"id":"1909.12223","title":"PairNorm: Tackling Oversmoothing in GNNs","created":"2019-09-26","cited_by_count":297},{"id":"2307.03393","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","created":"2023-07-07","cited_by_count":274},{"id":"2305.10037","title":"Can Language Models Solve Graph Problems in Natural Language?","created":"2023-05-17","cited_by_count":252},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"2002.04025","title":"Can Graph Neural Networks Count Substructures?","created":"2020-02-10","cited_by_count":236},{"id":"2308.07134","title":"Language is All a Graph Needs","created":"2023-08-14","cited_by_count":220},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217},{"id":"2010.13993","title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","created":"2020-10-27","cited_by_count":202},{"id":"1907.03199","title":"What graph neural networks cannot learn: depth vs width","created":"2019-07-06","cited_by_count":201},{"id":"2010.01179","title":"The Surprising Power of Graph Neural Networks with Random Node Initialization","created":"2020-10-02","cited_by_count":198},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2002.03155","title":"Random Features Strengthen Graph Neural Networks","created":"2020-02-08","cited_by_count":186},{"id":"2106.06981","title":"Thinking Like Transformers","created":"2021-06-13","cited_by_count":184},{"id":"2310.04560","title":"Talk like a Graph: Encoding Graphs for Large Language Models","created":"2023-10-06","cited_by_count":176},{"id":"1905.12560","title":"On the equivalence between graph isomorphism testing and function approximation with GNNs","created":"2019-05-29","cited_by_count":172},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169},{"id":"2110.03753","title":"From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness","created":"2021-10-07","cited_by_count":155},{"id":"2210.14709","title":"Learning on Large-scale Text-attributed Graphs via Variational Inference","created":"2022-10-26","cited_by_count":155},{"id":"1903.02541","title":"Relational Pooling for Graph Representations","created":"2019-03-06","cited_by_count":150},{"id":"2305.19523","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","created":"2023-05-31","cited_by_count":133},{"id":"2111.06283","title":"DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks","created":"2021-11-11","cited_by_count":118},{"id":"2310.01089","title":"GraphText: Graph Reasoning in Text Space","created":"2023-10-02","cited_by_count":111},{"id":"2106.04319","title":"Breaking the Limits of Message Passing Graph Neural Networks","created":"2021-06-08","cited_by_count":101},{"id":"2211.15779","title":"Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature","created":"2022-11-28","cited_by_count":98},{"id":"2302.06835","title":"Understanding Oversquashing in GNNs through the Lens of Effective Resistance","created":"2023-02-14","cited_by_count":97},{"id":"2005.00178","title":"On the Benefits of Invariance in Neural Networks","created":"2020-05-01","cited_by_count":79},{"id":"2405.18512","title":"Understanding Transformer Reasoning Capabilities via Graph Algorithms","created":"2024-05-28","cited_by_count":67},{"id":"2212.02374","title":"On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networks","created":"2022-12-05","cited_by_count":64},{"id":"2306.03589","title":"How does over-squashing affect the power of GNNs?","created":"2023-06-06","cited_by_count":53},{"id":"2305.16102","title":"Demystifying Oversmoothing in Attention-Based Graph Neural Networks","created":"2023-05-25","cited_by_count":49},{"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":"2401.08514","title":"Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness","created":"2024-01-16","cited_by_count":39},{"id":"2402.01107","title":"Simulation of Graph Algorithms with Looped Transformers","created":"2024-02-02","cited_by_count":30},{"id":"2306.02866","title":"Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance","created":"2023-06-05","cited_by_count":26},{"id":"2206.11010","title":"Agent-based Graph Neural Networks","created":"2022-06-22","cited_by_count":13},{"id":"2310.07430","title":"Non-backtracking Graph Neural Networks","created":"2023-10-11","cited_by_count":7},{"id":"2006.11947","title":"How to Count Triangles, without Seeing the Whole Graph","created":"2020-06-22","cited_by_count":6},{"id":"2107.12460","title":"Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers","created":"2021-07-26","cited_by_count":6},{"id":"2404.19288","title":"Training-free Graph Neural Networks and the Power of Labels as Features","created":"2024-04-30","cited_by_count":5},{"id":"2406.11814","title":"Stochastic Neural Network Symmetrisation in Markov Categories","created":"2024-06-17","cited_by_count":5},{"id":"2312.05905","title":"Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings","created":"2023-12-10","cited_by_count":4},{"id":"2206.09182","title":"Coin Flipping Neural Networks","created":"2022-06-18","cited_by_count":3},{"id":"1708.07967","title":"Faster Clustering via Non-Backtracking Random Walks","created":"2017-08-26","cited_by_count":2},{"id":"2111.11840","title":"Subgraph Permutation Equivariant Networks","created":"2021-11-23","cited_by_count":2},{"id":"2308.04412","title":"Probabilistic Invariant Learning with Randomized Linear Classifiers","created":"2023-08-08","cited_by_count":2},{"id":"1709.00869","title":"Estimating graph parameters with random walks","created":"2017-09-04","cited_by_count":1}],"next_cursor":null}