DARTS
E899016
differentiable architecture search algorithm
gradient-based optimization method for architectures
neural architecture search method
DARTS is a widely used differentiable neural architecture search method that optimizes network structures in a continuous space using gradient-based techniques.
All labels observed (1)
| Label | Occurrences |
|---|---|
| DARTS canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T11003095 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DARTS Context triple: [Neural Architecture Search, notableMethod, DARTS]
-
A.
Hearts & Darts
"Hearts & Darts" is a song by American rapper and producer Baby Keem, known for his melodic trap style and introspective lyrics.
-
B.
Bowling
Bowling is a village on the River Clyde in West Dunbartonshire, Scotland, known for its historic harbour and role as a transport hub at the western end of the Forth and Clyde Canal.
-
C.
Bowling
"Bowling" is a stylistically distinctive split-perspective episode of the sitcom *Malcolm in the Middle* that shows two alternate versions of the same night depending on whether Lois or Hal takes the boys to a bowling alley.
-
D.
H.O.R.S.E.
H.O.R.S.E. is a mixed poker format that rotates through several different poker variants, testing players’ versatility and all-around skill.
-
E.
Bullseye
"Bullseye" is a thriller novel in James Patterson and Michael Ledwidge's Michael Bennett series, following the NYPD detective as he races to stop an assassination plot against the U.S. president.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: DARTS Target entity description: DARTS is a widely used differentiable neural architecture search method that optimizes network structures in a continuous space using gradient-based techniques.
-
A.
Hearts & Darts
"Hearts & Darts" is a song by American rapper and producer Baby Keem, known for his melodic trap style and introspective lyrics.
-
B.
Bowling
Bowling is a village on the River Clyde in West Dunbartonshire, Scotland, known for its historic harbour and role as a transport hub at the western end of the Forth and Clyde Canal.
-
C.
Bowling
"Bowling" is a stylistically distinctive split-perspective episode of the sitcom *Malcolm in the Middle* that shows two alternate versions of the same night depending on whether Lois or Hal takes the boys to a bowling alley.
-
D.
H.O.R.S.E.
H.O.R.S.E. is a mixed poker format that rotates through several different poker variants, testing players’ versatility and all-around skill.
-
E.
Bullseye
"Bullseye" is a thriller novel in James Patterson and Michael Ledwidge's Michael Bennett series, following the NYPD detective as he races to stop an assassination plot against the U.S. president.
- F. None of above. chosen
Statements (48)
| Predicate | Object |
|---|---|
| instanceOf |
differentiable architecture search algorithm
ⓘ
gradient-based optimization method for architectures ⓘ neural architecture search method ⓘ |
| advantage |
enables end-to-end differentiable architecture optimization
ⓘ
significantly reduces search cost compared to RL-based NAS ⓘ |
| appliedTo |
CIFAR-10
NERFINISHED
ⓘ
ImageNet NERFINISHED ⓘ image classification ⓘ |
| category | weight-sharing NAS method ⓘ |
| citationTitle | DARTS: Differentiable Architecture Search NERFINISHED ⓘ |
| comparedTo |
evolutionary algorithm based NAS methods
ⓘ
reinforcement learning based NAS methods ⓘ |
| field |
deep learning
ⓘ
machine learning ⓘ neural architecture search ⓘ |
| fullName | Differentiable Architecture Search NERFINISHED ⓘ |
| implementation | commonly implemented in PyTorch ⓘ |
| influenced | many subsequent differentiable NAS methods ⓘ |
| inspired |
FairDARTS
NERFINISHED
ⓘ
PC-DARTS NERFINISHED ⓘ ProxylessNAS NERFINISHED ⓘ RobustDARTS NERFINISHED ⓘ |
| introduces | architecture parameters (alphas) ⓘ |
| limitation |
can overfit to validation set
ⓘ
prone to performance collapse in some settings ⓘ tends to prefer parameter-heavy operations ⓘ |
| objective | validation performance ⓘ |
| optimizationType | bilevel optimization problem ⓘ |
| optimizes |
architecture parameters jointly with network weights
ⓘ
cell-based network structures ⓘ neural network architectures ⓘ |
| output | discrete neural network architecture ⓘ |
| proposedBy |
Hanxiao Liu
NERFINISHED
ⓘ
Karen Simonyan NERFINISHED ⓘ Yiming Yang NERFINISHED ⓘ |
| publicationYear | 2019 ⓘ |
| publishedIn | International Conference on Learning Representations NERFINISHED ⓘ |
| represents | discrete architectures in a continuous search space ⓘ |
| searchSpace |
cell-based directed acyclic graphs
ⓘ
operations on edges between nodes ⓘ |
| searchStrategy |
alternating optimization of weights and architecture parameters
ⓘ
gradient-based search in continuous space ⓘ |
| selects | operations with highest architecture weights ⓘ |
| trainingObjective | minimize training loss with respect to network weights ⓘ |
| uses |
bilevel optimization
ⓘ
continuous relaxation of architecture choices ⓘ gradient-based optimization ⓘ |
| validationObjective | minimize validation loss with respect to architecture parameters ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: DARTS Description of subject: DARTS is a widely used differentiable neural architecture search method that optimizes network structures in a continuous space using gradient-based techniques.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.