{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/affinitynet-semi-supervised-few-shot-learning","title":"AffinityNet: semi-supervised few-shot learning for disease type prediction","arxiv_id":"1805.08905","date":"2018-05-22","proceeding":null,"authors":["Tianle Ma","Aidong Zhang"],"abstract":"While deep learning has achieved great success in computer vision and many\nother fields, currently it does not work very well on patient genomic data with\nthe \"big p, small N\" problem (i.e., a relatively small number of samples with\nhigh-dimensional features). In order to make deep learning work with a small\namount of training data, we have to design new models that facilitate few-shot\nlearning. Here we present the Affinity Network Model (AffinityNet), a data\nefficient deep learning model that can learn from a limited number of training\nexamples and generalize well. The backbone of the AffinityNet model consists of\nstacked k-Nearest-Neighbor (kNN) attention pooling layers. The kNN attention\npooling layer is a generalization of the Graph Attention Model (GAM), and can\nbe applied to not only graphs but also any set of objects regardless of whether\na graph is given or not. As a new deep learning module, kNN attention pooling\nlayers can be plugged into any neural network model just like convolutional\nlayers. As a simple special case of kNN attention pooling layer, feature\nattention layer can directly select important features that are useful for\nclassification tasks. Experiments on both synthetic data and cancer genomic\ndata from TCGA projects show that our AffinityNet model has better\ngeneralization power than conventional neural network models with little\ntraining data. The code is freely available at\nhttps://github.com/BeautyOfWeb/AffinityNet .","url_abs":"http://arxiv.org/abs/1805.08905v2","url_pdf":"http://arxiv.org/pdf/1805.08905v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"affinitynet-semi-supervised-few-shot-learning","repo_url":"https://github.com/BeautyOfWeb/AffinityNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"graph-attention","task_name":"Graph Attention"},{"task_slug":"type-prediction","task_name":"Type prediction"},{"task_slug":"type","task_name":"Vocal Bursts Type Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}