{"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"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":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294},{"id":"1907.12009","title":"Representation Degeneration Problem in Training Natural Language Generation Models","created":"2019-07-28","cited_by_count":255},{"id":"1602.04485","title":"Benefits of depth in neural networks","created":"2016-02-14","cited_by_count":250},{"id":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"id":"1906.08230","title":"Evaluating Protein Transfer Learning with TAPE","created":"2019-06-19","cited_by_count":231},{"id":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211},{"id":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","cited_by_count":194},{"id":"2007.06225","title":"ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing","created":"2020-07-13","cited_by_count":162},{"id":"2206.13517","title":"ProGen2: Exploring the Boundaries of Protein Language Models","created":"2022-06-27","cited_by_count":159},{"id":"2010.16103","title":"Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning","created":"2020-10-30","cited_by_count":149},{"id":"1811.03378","title":"Activation Functions: Comparison of trends in Practice and Research for Deep Learning","created":"2018-11-08","cited_by_count":130},{"id":"2004.03497","title":"ProGen: Language Modeling for Protein Generation","created":"2020-03-08","cited_by_count":128},{"id":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127},{"id":"2403.03234","title":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","created":"2024-03-05","cited_by_count":113},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112},{"id":"2402.08678","title":"Graph Mamba: Towards Learning on Graphs with State Space Models","created":"2024-02-13","cited_by_count":86},{"id":"2206.02096","title":"PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding","created":"2022-06-05","cited_by_count":77},{"id":"2201.11147","title":"OntoProtein: Protein Pretraining With Gene Ontology Embedding","created":"2022-01-23","cited_by_count":70},{"id":"2404.07839","title":"RecurrentGemma: Moving Past Transformers for Efficient Open Language Models","created":"2024-04-11","cited_by_count":64},{"id":"2202.08871","title":"Graph Data Augmentation for Graph Machine Learning: A Survey","created":"2022-02-17","cited_by_count":62},{"id":"2405.12609","title":"Mamba in Speech: Towards an Alternative to Self-Attention","created":"2024-05-21","cited_by_count":60},{"id":"2010.11711","title":"Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction","created":"2020-10-22","cited_by_count":41},{"id":"1902.00249","title":"ProteinNet: a standardized data set for machine learning of protein structure","created":"2019-02-01","cited_by_count":39},{"id":"2406.03344","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","created":"2024-06-05","cited_by_count":37},{"id":"2306.06156","title":"PoET: A generative model of protein families as sequences-of-sequences","created":"2023-06-09","cited_by_count":29},{"id":"1609.07959","title":"Multiplicative LSTM for sequence modelling","created":"2016-09-26","cited_by_count":27},{"id":"2407.06324","title":"B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory","created":"2024-07-08","cited_by_count":26},{"id":"2310.03320","title":"BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs","created":"2023-10-05","cited_by_count":25},{"id":"2012.02679","title":"What is a meaningful representation of protein sequences?","created":"2020-11-28","cited_by_count":22},{"id":"2110.15527","title":"Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model","created":"2021-10-29","cited_by_count":20},{"id":"2211.16742","title":"Protein Language Models and Structure Prediction: Connection and Progression","created":"2022-11-30","cited_by_count":17},{"id":"2205.14368","title":"Going Deeper into Permutation-Sensitive Graph Neural Networks","created":"2022-05-28","cited_by_count":15},{"id":"2103.10334","title":"Structure Inducing Pre-Training","created":"2021-03-18","cited_by_count":10},{"id":"2111.11638","title":"Network In Graph Neural Network","created":"2021-11-23","cited_by_count":8},{"id":"2105.06035","title":"GIPA: General Information Propagation Algorithm for Graph Learning","created":"2021-05-13","cited_by_count":5}],"next_cursor":null}