<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/xsl'?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T10:26:20Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/120981" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/120981</identifier><datestamp>2026-05-15T17:52:55Z</datestamp><setSpec>com_1813_35</setSpec><setSpec>col_1813_47</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Sheshanarayana, Rahul</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="chair" lang="en_US">You, Fengqi</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Acharya, Jayadev</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-04-02T19:05:16Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2026-04-02T19:05:16Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2025-12</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Submission ID: 12347</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Publication ID: 31934997</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/120981</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="doi">https://doi.org/10.7298/rtyv-3e85</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="bibid">17423314</dim:field>
   <dim:field mdschema="dc" element="description" lang="en_US">45 pages</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Knowledge distillation (KD) is a powerful model compression technique that transfers knowledge from complex teacher models to compact student models, reducing computational costs while preserving predictive accuracy. This study investigated KD's efficacy in molecular property prediction across domain-specific and cross-domain tasks, leveraging state-of-the-art graph neural networks (SchNet, DimeNet++, and TensorNet). In the domain-specific setting, KD improved regression performance across diverse quantum mechanical properties in the QM9 dataset, with DimeNet++ student models achieving up to a 90% improvement in R^2 compared to non-KD baselines. Notably, in certain cases, smaller student models achieved comparable or even superior R^2 improvements while being 2× smaller, highlighting KD’s ability to enhance efficiency without sacrificing predictive performance. Cross-domain evaluations further demonstrated KD’s adaptability, where embeddings from QM9-trained teacher models enhanced predictions for ESOL (water solubility of molecules) and FreeSolv (hydration free energy of molecules), with SchNet exhibiting the highest gains of approximately 65% in water solubility predictions. Embedding analysis revealed substantial student-teacher alignment gains, with the relative shift in cosine similarity distribution peaks reaching up to 1.0 across student models. These findings highlighted KD as a robust strategy for enhancing molecular representation learning, with implications for cheminformatics, materials science, and drug discovery.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Graph neural networks</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Knowledge distillation</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Machine learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Scalability</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">KNOWLEDGE DISTILLATION FOR MOLECULAR PROPERTY PREDICTION</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">dissertation or thesis</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="discipline">Systems Engineering</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="grantor">Cornell University</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="level">Master of Science</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="name">M.S., Systems Engineering</dim:field>
   <dim:field mdschema="dcterms" element="license">https://hdl.handle.net/1813/59810.2</dim:field>
   <dim:field mdschema="dspace" element="entity" qualifier="type">Publication</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="collection" authority="https://ecommons.cornell.edu/handle/1813/47" confidence="600">Cornell Theses and Dissertations</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="author">Sheshanarayana, Rahul</dim:field>
   <dim:field mdschema="cris" element="virtualsource" qualifier="collection">5893a6ea-7af3-41d7-abc6-04bcd26ab5df</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="cerif" element="openaire" authority="" confidence="-1">&lt;Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="b38a13e5-fe58-498a-9d7d-3726f4b92457">
	&lt;Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843&lt;/Type>
	&lt;Language>en&lt;/Language>
   	&lt;Title>KNOWLEDGE DISTILLATION FOR MOLECULAR PROPERTY PREDICTION&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2025-12&lt;/PublicationDate>
   	&lt;DOI>https://doi.org/10.7298/rtyv-3e85&lt;/DOI>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Sheshanarayana, Rahul&lt;/DisplayName>
         	&lt;Affiliation>
         		&lt;OrgUnit>
         		&lt;/OrgUnit>
         	&lt;/Affiliation>
      	&lt;/Author>
	&lt;/Authors>
   	&lt;Editors>
	&lt;/Editors>
    &lt;Publishers>
        &lt;Publisher>
            &lt;OrgUnit />
        &lt;/Publisher>
    &lt;/Publishers>
    &lt;Keyword>Graph neural networks&lt;/Keyword>
    &lt;Keyword>Knowledge distillation&lt;/Keyword>
    &lt;Keyword>Machine learning&lt;/Keyword>
    &lt;Keyword>Scalability&lt;/Keyword>
   	&lt;Abstract>Knowledge distillation (KD) is a powerful model compression technique that transfers knowledge from complex teacher models to compact student models, reducing computational costs while preserving predictive accuracy. This study investigated KD&amp;apos;s efficacy in molecular property prediction across domain-specific and cross-domain tasks, leveraging state-of-the-art graph neural networks (SchNet, DimeNet++, and TensorNet). In the domain-specific setting, KD improved regression performance across diverse quantum mechanical properties in the QM9 dataset, with DimeNet++ student models achieving up to a 90% improvement in R^2 compared to non-KD baselines. Notably, in certain cases, smaller student models achieved comparable or even superior R^2 improvements while being 2× smaller, highlighting KD’s ability to enhance efficiency without sacrificing predictive performance. Cross-domain evaluations further demonstrated KD’s adaptability, where embeddings from QM9-trained teacher models enhanced predictions for ESOL (water solubility of molecules) and FreeSolv (hydration free energy of molecules), with SchNet exhibiting the highest gains of approximately 65% in water solubility predictions. Embedding analysis revealed substantial student-teacher alignment gains, with the relative shift in cosine similarity distribution peaks reaching up to 1.0 across student models. These findings highlighted KD as a robust strategy for enhancing molecular representation learning, with implications for cheminformatics, materials science, and drug discovery.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>