随笔分类 - Representation Learning
摘要：目录概符号说明S4D代码 Gu A., Gupta A., Goel K. and Re C. On the parameterization and initialization of diagonal state space models. NeurIPS, 2022. 概 Mamba 系列第四
阅读全文
摘要：目录概符号说明S4代码 Gu A., Goel K. and Re C. Efficiently modeling long sequences with structured state spaces. NeurIPS, 2022. 概 Mamba 系列第三作. 符号说明 \(u(t) \in \
阅读全文
摘要：目录概符号说明LSSL和其它方法的联系代码 Gu A., Johnson I., Goel K., Saab K., Dao T., Rudra A., and Re C. Combining recurrent, convolutional, and continuous-time models
阅读全文
摘要：目录概Motivation代码 Gu A., Dao T., Ermon S., Rudra A. and Re C. HiPPO: Recurrent memory with optimal polynomial projections. NIPS, 2021. 概 看下最近很火的 Mamba 的
阅读全文
摘要：目录概符号说明Unlearning LayersFusing Unlearning Layers代码 Chen J. and Yang D. Unlearn what you want to forget: efficient unlearning for llms. 2024. 概 本文提出一种
阅读全文
摘要：目录概主要内容BERT-FlowBERT-Whitening代码 [1] Li B., Zhou H., He J., Wang M., Yang Y. and Li L. On the sentence embeddings from pre-trained language models. AC
阅读全文
摘要：目录概TransE|H|R Bordes A., Usunier N., Garcia-Duran A., Weston J. and Yakhnenko O. Translating embeddings for modeling multi-relational data. NIPS, 2013
阅读全文
摘要：目录概符号说明ULTRA (a method for Unified, Learnable, and TRAnsferable KG representations)Relation Graph ConstructionConditional Relation Representations代码 G
阅读全文
摘要：目录概符号说明GPR-GNN代码 Chien E., Peng J., Li P. and Milenkovic O. Adaptive universal generalized pagerank graph neural network. ICLR, 2021. 概 GPR-GNN 自适应地学习
阅读全文
摘要：目录概符号说明MotivationROLAND训练策略Live-update Evaluation代码 You J., Du T. and Leskovec J. ROLAND: Graph learning framework for dynamic graphs. KDD, 2022. 概 dy
阅读全文
摘要：目录概符号说明EvolveGCN代码 Pareja A., Domeniconi G., Chen J., Ma T., Suzumura T., Kanezashi H., Kaler T., Schardl T. B. and Leiserson C. E. EvolveGCN: Evolvin
阅读全文
摘要：目录概符号说明MotivationGCOND代码 Jin W., Zhao L., Zhang S., Liu Y., Tang J. and Shah N. Graph condensation for graph neural networks. ICLR, 2022. 概 图上做压缩的工作.
阅读全文
摘要：目录概Noise contrastive estimation Mnih A. and Teh Y. W. A fast and simple algorithm for training neural probabilistic language models. ICML, 2012. 概 NCE
阅读全文
摘要：目录概符号说明DeepWalk代码 Perozzi B., AI-Rfou R. and Skiena S. DeepWalk: Online learning of social representations. KDD, 2014. 概 经典的 graph embedding 学习方法. 符号说
阅读全文
摘要：目录概符号说明MotivationNewtonNet代码 Xu J., Dai E., Luo D>, Zhang X. and Wang S. Learning graph filters for spectral gnns via newton interpolation. 2023. 概 令谱
阅读全文
摘要：目录概符号说明DSF代码 Guo J., Huang K, Yi X. and Zhang R. Graph neural networks with diverse spectral filtering. WWW, 2023. 概 为每个结点赋予不同的多项式系数. 符号说明 \(\mathcal{
阅读全文
摘要：目录概符号说明Spectral GNNChoice of Basis for Polynomial FiltersJacobiConv代码 Wang X. and Zhang M. How powerful are spectral graph neural networks? ICML, 2022
阅读全文
摘要：目录概符号说明GATv2代码 Brody S., Alon U. and Yahav E. How attentive are graph attention networks? ICLR, 2022. 概 作者发现了 GAT 的 attention 并不能够抓住边的重要性, 于是提出了 GATv2
阅读全文
摘要：目录概符号说明Shadow-GNN代码 Zeng H., Zhang M., Xia Y., Srivastava A., Malevich A., Kannan R., Prasanna V., Jin L. and Chen R. Decoupling the depth and scope o
阅读全文
摘要：目录概符号说明AirGNN代码 Liu X., Ding J., Jin W., Xu H., Ma Y., Liu Z. and Tang J. Graph neural networks with adaptive residual. NIPS, 2021. 概 基于 UGNN 框架的一个更加鲁
阅读全文
