{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/164495"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/164495","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Sampling Methods for Fast and Versatile GNN Training","abstract":"Graph neural networks (GNNs) have become a commonly used class of machine learning models that achieve state-of-the-art performance in various applications. A prevalent and effective approach for applying GNNs on large datasets involves mini-batch training with sampled neighborhoods. Numerous sampling algorithms have emerged, some tailored for specific GNN applications. In this thesis, I explore ways to improve the efficiency and expressivity of existing and emerging sampling schemes. First, I explore system solutions to facilitate the development of fast implementations of different sampling methods. I introduce FlexSample, a system for efficiently incorporating custom sampling algorithms into GNN training. FlexSample leverages the types of performance optimizations found in SALIENT, a state-of-the-art system for fast training of GNNs with node-wise sampling. In experiments with 4 GNN models which use layer-wise and subgraph sampling, FlexSample achieves up to 1.3× speed-up for end-to-end training over PyTorch Geometric with the same sampling code. Furthermore, FlexSample extends SALIENT with highly-optimized C++ implementations of FastGCN and LADIES layer-wise sampling, which achieve 2×–5× speed-up over their respective Python implementations. Second, I introduce a novel framework for learning neighbor sampling distributions as part of GNN training. Key components of this framework, which I name PertinenceSample, are: (i) a differentiable approximation of node-wise sampling for GNNs; and (ii) a parametrization of node sampling distributions as node- or edge-wise weights of attention-like GNN layers. I present an initial exploration of the potential of PertinenceSample for improving node classification accuracy in the presence of noisy edges. Specifically, in two synthetic experiments where roughly half of a node’s neighbors may have similar features but different labels, I demonstrate that extending a GraphSAGE model with a 2-layer perceptron for learning the PertinenceSample weights can improve classification accuracy from 50%–75% to (nearly) 100%.","abstract_html":"Graph neural networks (GNNs) have become a commonly used class of machine learning models that achieve state-of-the-art performance in various applications. A prevalent and effective approach for applying GNNs on large datasets involves mini-batch training with sampled neighborhoods. Numerous sampling algorithms have emerged, some tailored for specific GNN applications. In this thesis, I explore ways to improve the efficiency and expressivity of existing and emerging sampling schemes. First, I explore system solutions to facilitate the development of fast implementations of different sampling methods. I introduce FlexSample, a system for efficiently incorporating custom sampling algorithms into GNN training. FlexSample leverages the types of performance optimizations found in SALIENT, a state-of-the-art system for fast training of GNNs with node-wise sampling. In experiments with 4 GNN models which use layer-wise and subgraph sampling, FlexSample achieves up to 1.3× speed-up for end-to-end training over PyTorch Geometric with the same sampling code. Furthermore, FlexSample extends SALIENT with highly-optimized C++ implementations of FastGCN and LADIES layer-wise sampling, which achieve 2×–5× speed-up over their respective Python implementations. Second, I introduce a novel framework for learning neighbor sampling distributions as part of GNN training. Key components of this framework, which I name PertinenceSample, are: (i) a differentiable approximation of node-wise sampling for GNNs; and (ii) a parametrization of node sampling distributions as node- or edge-wise weights of attention-like GNN layers. I present an initial exploration of the potential of PertinenceSample for improving node classification accuracy in the presence of noisy edges. Specifically, in two synthetic experiments where roughly half of a node’s neighbors may have similar features but different labels, I demonstrate that extending a GraphSAGE model with a 2-layer perceptron for learning the PertinenceSample weights can improve classification accuracy from 50%–75% to (nearly) 100%.","abstract_has_math":false,"creators":["Alkhatib, Obada"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Leiserson, Charles E.","Kaler, Timothy","Iliopoulos, Alexandros-Stavros"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-09","date_published":"2022-09","updated_at":"2026-07-22T22:21:51Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/164495","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Leiserson, Charles E.","Kaler, Timothy","Iliopoulos, Alexandros-Stavros"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Alkhatib, Obada"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-01-12T19:40:26Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-12T19:40:26Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-09"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/164495"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Graph neural networks (GNNs) have become a commonly used class of machine learning models that achieve state-of-the-art performance in various applications. A prevalent and effective approach for applying GNNs on large datasets involves mini-batch training with sampled neighborhoods. Numerous sampling algorithms have emerged, some tailored for specific GNN applications. In this thesis, I explore ways to improve the efficiency and expressivity of existing and emerging sampling schemes. First, I explore system solutions to facilitate the development of fast implementations of different sampling methods. I introduce FlexSample, a system for efficiently incorporating custom sampling algorithms into GNN training. FlexSample leverages the types of performance optimizations found in SALIENT, a state-of-the-art system for fast training of GNNs with node-wise sampling. In experiments with 4 GNN models which use layer-wise and subgraph sampling, FlexSample achieves up to 1.3× speed-up for end-to-end training over PyTorch Geometric with the same sampling code. Furthermore, FlexSample extends SALIENT with highly-optimized C++ implementations of FastGCN and LADIES layer-wise sampling, which achieve 2×–5× speed-up over their respective Python implementations. Second, I introduce a novel framework for learning neighbor sampling distributions as part of GNN training. Key components of this framework, which I name PertinenceSample, are: (i) a differentiable approximation of node-wise sampling for GNNs; and (ii) a parametrization of node sampling distributions as node- or edge-wise weights of attention-like GNN layers. I present an initial exploration of the potential of PertinenceSample for improving node classification accuracy in the presence of noisy edges. Specifically, in two synthetic experiments where roughly half of a node’s neighbors may have similar features but different labels, I demonstrate that extending a GraphSAGE model with a 2-layer perceptron for learning the PertinenceSample weights can improve classification accuracy from 50%–75% to (nearly) 100%."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Sampling Methods for Fast and Versatile GNN Training"]}]}],"canonical_facts":{"dc:contributor.advisor":["Leiserson, Charles E.","Kaler, Timothy","Iliopoulos, Alexandros-Stavros"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Alkhatib, Obada"],"dc:date.accessioned":["2026-01-12T19:40:26Z"],"dc:date.available":["2026-01-12T19:40:26Z"],"dc:date.issued":["2022-09"],"dc:description.abstract":["Graph neural networks (GNNs) have become a commonly used class of machine learning models that achieve state-of-the-art performance in various applications. A prevalent and effective approach for applying GNNs on large datasets involves mini-batch training with sampled neighborhoods. Numerous sampling algorithms have emerged, some tailored for specific GNN applications. In this thesis, I explore ways to improve the efficiency and expressivity of existing and emerging sampling schemes. First, I explore system solutions to facilitate the development of fast implementations of different sampling methods. I introduce FlexSample, a system for efficiently incorporating custom sampling algorithms into GNN training. FlexSample leverages the types of performance optimizations found in SALIENT, a state-of-the-art system for fast training of GNNs with node-wise sampling. In experiments with 4 GNN models which use layer-wise and subgraph sampling, FlexSample achieves up to 1.3× speed-up for end-to-end training over PyTorch Geometric with the same sampling code. Furthermore, FlexSample extends SALIENT with highly-optimized C++ implementations of FastGCN and LADIES layer-wise sampling, which achieve 2×–5× speed-up over their respective Python implementations. Second, I introduce a novel framework for learning neighbor sampling distributions as part of GNN training. Key components of this framework, which I name PertinenceSample, are: (i) a differentiable approximation of node-wise sampling for GNNs; and (ii) a parametrization of node sampling distributions as node- or edge-wise weights of attention-like GNN layers. I present an initial exploration of the potential of PertinenceSample for improving node classification accuracy in the presence of noisy edges. Specifically, in two synthetic experiments where roughly half of a node’s neighbors may have similar features but different labels, I demonstrate that extending a GraphSAGE model with a 2-layer perceptron for learning the PertinenceSample weights can improve classification accuracy from 50%–75% to (nearly) 100%."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/164495"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Sampling Methods for Fast and Versatile GNN Training"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:51Z"}