Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094896511> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3094896511 endingPage "60" @default.
- W3094896511 startingPage "1" @default.
- W3094896511 abstract "We introduce an extension of the multi-instance learning problem where examples are organized as nested bags of instances (e.g., a document could be represented as a bag of sentences, which in turn are bags of words). This framework can be useful in various scenarios, such as text and image classification, but also supervised learning over graphs. As a further advantage, multi-multi instance learning enables a particular way of interpreting predictions and the decision function. Our approach is based on a special neural network layer, called bag-layer, whose units aggregate bags of inputs of arbitrary size. We prove theoretically that the associated class of functions contains all Boolean functions over sets of sets of instances and we provide empirical evidence that functions of this kind can be actually learned on semi-synthetic datasets. We finally present experiments on text classification, on citation graphs, and social graph data, which show that our model obtains competitive results with respect to accuracy when compared to other approaches such as convolutional networks on graphs, while at the same time it supports a general approach to interpret the learnt model, as well as explain individual predictions." @default.
- W3094896511 created "2020-11-09" @default.
- W3094896511 creator A5013544797 @default.
- W3094896511 creator A5014289413 @default.
- W3094896511 creator A5027422071 @default.
- W3094896511 date "2020-10-01" @default.
- W3094896511 modified "2023-09-23" @default.
- W3094896511 title "Learning and Interpreting Multi-Multi-Instance Learning Networks" @default.
- W3094896511 hasPublicationYear "2020" @default.
- W3094896511 type Work @default.
- W3094896511 sameAs 3094896511 @default.
- W3094896511 citedByCount "0" @default.
- W3094896511 crossrefType "journal-article" @default.
- W3094896511 hasAuthorship W3094896511A5013544797 @default.
- W3094896511 hasAuthorship W3094896511A5014289413 @default.
- W3094896511 hasAuthorship W3094896511A5027422071 @default.
- W3094896511 hasConcept C119857082 @default.
- W3094896511 hasConcept C132525143 @default.
- W3094896511 hasConcept C14036430 @default.
- W3094896511 hasConcept C154945302 @default.
- W3094896511 hasConcept C159985019 @default.
- W3094896511 hasConcept C192562407 @default.
- W3094896511 hasConcept C199360897 @default.
- W3094896511 hasConcept C2777212361 @default.
- W3094896511 hasConcept C2778029271 @default.
- W3094896511 hasConcept C41008148 @default.
- W3094896511 hasConcept C4679612 @default.
- W3094896511 hasConcept C78458016 @default.
- W3094896511 hasConcept C80444323 @default.
- W3094896511 hasConcept C86803240 @default.
- W3094896511 hasConceptScore W3094896511C119857082 @default.
- W3094896511 hasConceptScore W3094896511C132525143 @default.
- W3094896511 hasConceptScore W3094896511C14036430 @default.
- W3094896511 hasConceptScore W3094896511C154945302 @default.
- W3094896511 hasConceptScore W3094896511C159985019 @default.
- W3094896511 hasConceptScore W3094896511C192562407 @default.
- W3094896511 hasConceptScore W3094896511C199360897 @default.
- W3094896511 hasConceptScore W3094896511C2777212361 @default.
- W3094896511 hasConceptScore W3094896511C2778029271 @default.
- W3094896511 hasConceptScore W3094896511C41008148 @default.
- W3094896511 hasConceptScore W3094896511C4679612 @default.
- W3094896511 hasConceptScore W3094896511C78458016 @default.
- W3094896511 hasConceptScore W3094896511C80444323 @default.
- W3094896511 hasConceptScore W3094896511C86803240 @default.
- W3094896511 hasIssue "193" @default.
- W3094896511 hasLocation W30948965111 @default.
- W3094896511 hasOpenAccess W3094896511 @default.
- W3094896511 hasPrimaryLocation W30948965111 @default.
- W3094896511 hasRelatedWork W117742025 @default.
- W3094896511 hasRelatedWork W1647591404 @default.
- W3094896511 hasRelatedWork W1758923908 @default.
- W3094896511 hasRelatedWork W2139031914 @default.
- W3094896511 hasRelatedWork W2160668399 @default.
- W3094896511 hasRelatedWork W2168100051 @default.
- W3094896511 hasRelatedWork W2172099713 @default.
- W3094896511 hasRelatedWork W2200306556 @default.
- W3094896511 hasRelatedWork W2508478068 @default.
- W3094896511 hasRelatedWork W2534803673 @default.
- W3094896511 hasRelatedWork W2806373217 @default.
- W3094896511 hasRelatedWork W2898188206 @default.
- W3094896511 hasRelatedWork W2920144136 @default.
- W3094896511 hasRelatedWork W2963773915 @default.
- W3094896511 hasRelatedWork W2974832202 @default.
- W3094896511 hasRelatedWork W3121197195 @default.
- W3094896511 hasRelatedWork W3166852774 @default.
- W3094896511 hasRelatedWork W3174340586 @default.
- W3094896511 hasRelatedWork W3213425801 @default.
- W3094896511 hasRelatedWork W53551796 @default.
- W3094896511 hasVolume "21" @default.
- W3094896511 isParatext "false" @default.
- W3094896511 isRetracted "false" @default.
- W3094896511 magId "3094896511" @default.
- W3094896511 workType "article" @default.