{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1808.09781","title":"Self-Attentive Sequential Recommendation","created":"2018-08-20","cited_by_count":1184},{"id":"2002.02126","title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation","created":"2020-02-06","cited_by_count":1139},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1606.07792","title":"Wide & Deep Learning for Recommender Systems","created":"2016-06-24","cited_by_count":747},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"1905.08108","title":"Neural Graph Collaborative Filtering","created":"2019-05-20","cited_by_count":661},{"id":"1503.03578","title":"LINE: Large-scale Information Network Embedding","created":"2015-03-12","cited_by_count":582},{"id":"2006.09963","title":"GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training","created":"2020-06-17","cited_by_count":463},{"id":"2203.13366","title":"Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)","created":"2022-03-24","cited_by_count":402},{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378},{"id":"1905.07854","title":"KGAT: Knowledge Graph Attention Network for Recommendation","created":"2019-05-20","cited_by_count":343},{"id":"2010.10783","title":"Self-supervised Graph Learning for Recommendation","created":"2020-10-21","cited_by_count":305},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"1708.04617","title":"Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks","created":"2017-08-15","cited_by_count":126},{"id":"2303.13835","title":"Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited","created":"2023-03-24","cited_by_count":124},{"id":"1904.12575","title":"Knowledge Graph Convolutional Networks for Recommender Systems","created":"2019-03-18","cited_by_count":121},{"id":"1908.00413","title":"MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation","created":"2019-07-31","cited_by_count":121},{"id":"2206.05941","title":"Towards Universal Sequence Representation Learning for Recommender Systems","created":"2022-06-13","cited_by_count":121},{"id":"1902.06236","title":"Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences","created":"2019-02-17","cited_by_count":87},{"id":"2103.02631","title":"RotoGrad: Gradient Homogenization in Multitask Learning","created":"2021-03-03","cited_by_count":83},{"id":"2107.05315","title":"Contrastive Learning for Cold-Start Recommendation","created":"2021-07-12","cited_by_count":79},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67},{"id":"1904.11547","title":"Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings","created":"2019-04-25","cited_by_count":66},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60},{"id":"2111.04840","title":"Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods","created":"2021-11-08","cited_by_count":58},{"id":"2206.12811","title":"Towards Representation Alignment and Uniformity in Collaborative Filtering","created":"2022-06-26","cited_by_count":57},{"id":"2105.00522","title":"Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer","created":"2021-05-02","cited_by_count":45},{"id":"2302.01735","title":"Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective","created":"2023-02-03","cited_by_count":43},{"id":"2012.07064","title":"Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation","created":"2020-12-13","cited_by_count":42},{"id":"2007.03183","title":"MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation","created":"2020-07-07","cited_by_count":39},{"id":"2105.02254","title":"ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation","created":"2021-05-05","cited_by_count":39},{"id":"2105.04790","title":"Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks","created":"2021-05-11","cited_by_count":37},{"id":"2103.06137","title":"Task-adaptive Neural Process for User Cold-Start Recommendation","created":"2021-02-26","cited_by_count":32},{"id":"2209.13476","title":"Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels","created":"2022-09-27","cited_by_count":30},{"id":"1906.08511","title":"From Zero-Shot Learning to Cold-Start Recommendation","created":"2019-06-20","cited_by_count":29},{"id":"2206.02307","title":"Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillation","created":"2022-06-06","cited_by_count":27},{"id":"2207.07483","title":"A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation","created":"2022-07-15","cited_by_count":22},{"id":"2007.04833","title":"Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach","created":"2020-07-09","cited_by_count":20},{"id":"2111.08268","title":"Pre-training Graph Neural Network for Cross Domain Recommendation","created":"2021-11-16","cited_by_count":14},{"id":"2305.07633","title":"Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Training","created":"2023-05-12","cited_by_count":12},{"id":"2304.02689","title":"ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast","created":"2023-04-05","cited_by_count":9},{"id":"2202.03851","title":"MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation","created":"2022-02-08","cited_by_count":8},{"id":"2205.13795","title":"Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder","created":"2022-05-27","cited_by_count":8},{"id":"2211.07104","title":"MetaKRec: Collaborative Meta-Knowledge Enhanced Recommender System","created":"2022-11-14","cited_by_count":4}],"next_cursor":null}