CRII: III: Integrating Domain Knowledge via Interactive Multi-Task Learning View Homepage


Ontology type: schema:MonetaryGrant     


Grant Info

YEARS

2016-2019

FUNDING AMOUNT

174883 USD

ABSTRACT

The ever increasing availability of data has attracted a huge amount of effort building machine learning models from the data to unleash its hidden power. One ubiquitous finding about these machine learning tasks is that in most real-world applications the learning tasks are closely related to each other. Moreover, human experts in many domains can usually provide indispensable domain knowledge describing how these models are related. Maximally exploiting such knowledge is critical in building high quality machine learning models. This project will develop effective and efficient interactive algorithms and tools (including open source software) to enable knowledge discovery by integrating domain knowledge of task relatedness from human experts. The algorithms and tools developed in this project will directly impact biomedical informatics as they will be used to build disease progression models. The educational component of this project includes developing a new curriculum that incorporates research into the classroom and provides students from under-represented groups with opportunities to participate in research. Leveraging task relatedness, multi-task learning (MTL) simultaneously learns all related learning tasks and performs knowledge transfer among the tasks to improve the quality of models from all the tasks. Although there are numerous studies for MTL that assume different types of task relatedness, limited progress has been made in incorporating domain knowledge in MTL. This project will advance MTL by: (1) developing algorithms for knowledge aware multi-task feature learning which exploit domain knowledge of features to guide the selection of joint features from the learning tasks; (2) developing algorithms for knowledge aware multi-task relationship learning which utilize domain knowledge of tasks to guide the learning of task relationships; and (3) developing efficient and scalable optimization algorithms to facilitate effective interactive visualization. For further information see the project web page: http://jiayuzhou.github.io/projects/crii More... »

URL

http://www.nsf.gov/awardsearch/showAward?AWD_ID=1565596&HistoricalAwards=false

Related SciGraph Publications

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2208", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2208", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "amount": {
      "currency": "USD", 
      "type": "MonetaryAmount", 
      "value": "174883"
    }, 
    "description": "The ever increasing availability of data has attracted a huge amount of effort building machine learning models from the data to unleash its hidden power. One ubiquitous finding about these machine learning tasks is that in most real-world applications the learning tasks are closely related to each other. Moreover, human experts in many domains can usually provide indispensable domain knowledge describing how these models are related. Maximally exploiting such knowledge is critical in building high quality machine learning models. This project will develop effective and efficient interactive algorithms and tools (including open source software) to enable knowledge discovery by integrating domain knowledge of task relatedness from human experts. The algorithms and tools developed in this project will directly impact biomedical informatics as they will be used to build disease progression models. The educational component of this project includes developing a new curriculum that incorporates research into the classroom and provides students from under-represented groups with opportunities to participate in research. Leveraging task relatedness, multi-task learning (MTL) simultaneously learns all related learning tasks and performs knowledge transfer among the tasks to improve the quality of models from all the tasks. Although there are numerous studies for MTL that assume different types of task relatedness, limited progress has been made in incorporating domain knowledge in MTL. This project will advance MTL by: (1) developing algorithms for knowledge aware multi-task feature learning which exploit domain knowledge of features to guide the selection of joint features from the learning tasks; (2) developing algorithms for knowledge aware multi-task relationship learning which utilize domain knowledge of tasks to guide the learning of task relationships; and (3) developing efficient and scalable optimization algorithms to facilitate effective interactive visualization. For further information see the project web page: http://jiayuzhou.github.io/projects/crii", 
    "endDate": "2019-03-31T00:00:00Z", 
    "funder": {
      "id": "https://www.grid.ac/institutes/grid.457785.c", 
      "type": "Organization"
    }, 
    "id": "sg:grant.5064001", 
    "identifier": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "5064001"
        ]
      }, 
      {
        "name": "nsf_id", 
        "type": "PropertyValue", 
        "value": [
          "1565596"
        ]
      }
    ], 
    "inLanguage": [
      "en"
    ], 
    "keywords": [
      "classroom", 
      "quality", 
      "most real-world applications", 
      "model", 
      "huge amount", 
      "multi-task learning", 
      "high quality machine", 
      "further information", 
      "research", 
      "opportunity", 
      "open source software", 
      "educational component", 
      "machine learning models", 
      "task", 
      "efficient interactive algorithms", 
      "different types", 
      "learning task", 
      "tool", 
      "learning", 
      "indispensable domain knowledge", 
      "scalable optimization algorithms", 
      "limited progress", 
      "related learning tasks", 
      "task relatedness", 
      "disease progression model", 
      "new curriculum", 
      "availability", 
      "aware multi-task relationship", 
      "students", 
      "task relationships", 
      "algorithms", 
      "aware multi-task feature", 
      "domain knowledge", 
      "selection", 
      "biomedical informatics", 
      "data", 
      "CrII", 
      "efforts", 
      "numerous studies", 
      "knowledge", 
      "Interactive Multi-Task Learning", 
      "knowledge transfer", 
      "groups", 
      "joint features", 
      "machine", 
      "many domains", 
      "features", 
      "project web page", 
      "such knowledge", 
      "hidden power", 
      "effective interactive visualization", 
      "project", 
      "human experts", 
      "knowledge discovery"
    ], 
    "name": "CRII: III: Integrating Domain Knowledge via Interactive Multi-Task Learning", 
    "recipient": [
      {
        "id": "https://www.grid.ac/institutes/grid.17088.36", 
        "type": "Organization"
      }, 
      {
        "affiliation": {
          "id": "https://www.grid.ac/institutes/grid.17088.36", 
          "name": "Michigan State University", 
          "type": "Organization"
        }, 
        "familyName": "Zhou", 
        "givenName": "Jiayu", 
        "id": "sg:person.01266530647.08", 
        "type": "Person"
      }, 
      {
        "member": "sg:person.01266530647.08", 
        "roleName": "PI", 
        "type": "Role"
      }
    ], 
    "sameAs": [
      "https://app.dimensions.ai/details/grant/grant.5064001"
    ], 
    "sdDataset": "grants", 
    "sdDatePublished": "2019-03-07T12:37", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com.uberresearch.data.processor/core_data/20181219_192338/projects/base/nsf_projects_8.xml.gz", 
    "startDate": "2016-05-01T00:00:00Z", 
    "type": "MonetaryGrant", 
    "url": "http://www.nsf.gov/awardsearch/showAward?AWD_ID=1565596&HistoricalAwards=false"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/grant.5064001'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/grant.5064001'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/grant.5064001'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/grant.5064001'


 

This table displays all metadata directly associated to this object as RDF triples.

98 TRIPLES      19 PREDICATES      76 URIs      68 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:grant.5064001 schema:about anzsrc-for:2208
2 schema:amount Nf0c27aacc3184d36b39148f5d16ea9a9
3 schema:description The ever increasing availability of data has attracted a huge amount of effort building machine learning models from the data to unleash its hidden power. One ubiquitous finding about these machine learning tasks is that in most real-world applications the learning tasks are closely related to each other. Moreover, human experts in many domains can usually provide indispensable domain knowledge describing how these models are related. Maximally exploiting such knowledge is critical in building high quality machine learning models. This project will develop effective and efficient interactive algorithms and tools (including open source software) to enable knowledge discovery by integrating domain knowledge of task relatedness from human experts. The algorithms and tools developed in this project will directly impact biomedical informatics as they will be used to build disease progression models. The educational component of this project includes developing a new curriculum that incorporates research into the classroom and provides students from under-represented groups with opportunities to participate in research. Leveraging task relatedness, multi-task learning (MTL) simultaneously learns all related learning tasks and performs knowledge transfer among the tasks to improve the quality of models from all the tasks. Although there are numerous studies for MTL that assume different types of task relatedness, limited progress has been made in incorporating domain knowledge in MTL. This project will advance MTL by: (1) developing algorithms for knowledge aware multi-task feature learning which exploit domain knowledge of features to guide the selection of joint features from the learning tasks; (2) developing algorithms for knowledge aware multi-task relationship learning which utilize domain knowledge of tasks to guide the learning of task relationships; and (3) developing efficient and scalable optimization algorithms to facilitate effective interactive visualization. For further information see the project web page: http://jiayuzhou.github.io/projects/crii
4 schema:endDate 2019-03-31T00:00:00Z
5 schema:funder https://www.grid.ac/institutes/grid.457785.c
6 schema:identifier N1786497811754af485cddb05de96fb6c
7 N40568014d0674017b0ae63fc773bb4c0
8 schema:inLanguage en
9 schema:keywords CrII
10 Interactive Multi-Task Learning
11 algorithms
12 availability
13 aware multi-task feature
14 aware multi-task relationship
15 biomedical informatics
16 classroom
17 data
18 different types
19 disease progression model
20 domain knowledge
21 educational component
22 effective interactive visualization
23 efficient interactive algorithms
24 efforts
25 features
26 further information
27 groups
28 hidden power
29 high quality machine
30 huge amount
31 human experts
32 indispensable domain knowledge
33 joint features
34 knowledge
35 knowledge discovery
36 knowledge transfer
37 learning
38 learning task
39 limited progress
40 machine
41 machine learning models
42 many domains
43 model
44 most real-world applications
45 multi-task learning
46 new curriculum
47 numerous studies
48 open source software
49 opportunity
50 project
51 project web page
52 quality
53 related learning tasks
54 research
55 scalable optimization algorithms
56 selection
57 students
58 such knowledge
59 task
60 task relatedness
61 task relationships
62 tool
63 schema:name CRII: III: Integrating Domain Knowledge via Interactive Multi-Task Learning
64 schema:recipient N33c7df58e468491483bb251c44197479
65 sg:person.01266530647.08
66 https://www.grid.ac/institutes/grid.17088.36
67 schema:sameAs https://app.dimensions.ai/details/grant/grant.5064001
68 schema:sdDatePublished 2019-03-07T12:37
69 schema:sdLicense https://scigraph.springernature.com/explorer/license/
70 schema:sdPublisher Ndd1a30512cd548c38c12c03352c3bffb
71 schema:startDate 2016-05-01T00:00:00Z
72 schema:url http://www.nsf.gov/awardsearch/showAward?AWD_ID=1565596&HistoricalAwards=false
73 sgo:license sg:explorer/license/
74 sgo:sdDataset grants
75 rdf:type schema:MonetaryGrant
76 N1786497811754af485cddb05de96fb6c schema:name nsf_id
77 schema:value 1565596
78 rdf:type schema:PropertyValue
79 N33c7df58e468491483bb251c44197479 schema:member sg:person.01266530647.08
80 schema:roleName PI
81 rdf:type schema:Role
82 N40568014d0674017b0ae63fc773bb4c0 schema:name dimensions_id
83 schema:value 5064001
84 rdf:type schema:PropertyValue
85 Ndd1a30512cd548c38c12c03352c3bffb schema:name Springer Nature - SN SciGraph project
86 rdf:type schema:Organization
87 Nf0c27aacc3184d36b39148f5d16ea9a9 schema:currency USD
88 schema:value 174883
89 rdf:type schema:MonetaryAmount
90 anzsrc-for:2208 schema:inDefinedTermSet anzsrc-for:
91 rdf:type schema:DefinedTerm
92 sg:person.01266530647.08 schema:affiliation https://www.grid.ac/institutes/grid.17088.36
93 schema:familyName Zhou
94 schema:givenName Jiayu
95 rdf:type schema:Person
96 https://www.grid.ac/institutes/grid.17088.36 schema:name Michigan State University
97 rdf:type schema:Organization
98 https://www.grid.ac/institutes/grid.457785.c schema:Organization
 




Preview window. Press ESC to close (or click here)


...