MétaCan
Menu
Back to cohort
Record W3006544536 · doi:10.48550/arxiv.2002.05825

An Inductive Bias for Distances: Neural Nets that Respect the Triangle\n Inequality

2020· preprint· en· W3006544536 on OpenAlexaff
Silviu Pitis, Harris Chan, Kiarash Jamali, Jimmy Ba

Bibliographic record

VenuearXiv (Cornell University) · 2020
Typepreprint
Languageen
FieldComputer Science
TopicAdvanced Graph Neural Networks
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsTriangle inequalityInductive biasSubadditivityArtificial neural networkMathematicsReinforcement learningMetric spaceMetric (unit)Euclidean spaceComputer scienceDiscrete mathematicsTheoretical computer scienceArtificial intelligenceCombinatoricsMulti-task learningTask (project management)

Abstract

fetched live from OpenAlex

Distances are pervasive in machine learning. They serve as similarity\nmeasures, loss functions, and learning targets; it is said that a good distance\nmeasure solves a task. When defining distances, the triangle inequality has\nproven to be a useful constraint, both theoretically--to prove convergence and\noptimality guarantees--and empirically--as an inductive bias. Deep metric\nlearning architectures that respect the triangle inequality rely, almost\nexclusively, on Euclidean distance in the latent space. Though effective, this\nfails to model two broad classes of subadditive distances, common in graphs and\nreinforcement learning: asymmetric metrics, and metrics that cannot be embedded\ninto Euclidean space. To address these problems, we introduce novel\narchitectures that are guaranteed to satisfy the triangle inequality. We prove\nour architectures universally approximate norm-induced metrics on\n$\\mathbb{R}^n$, and present a similar result for modified Input Convex Neural\nNetworks. We show that our architectures outperform existing metric approaches\nwhen modeling graph distances and have a better inductive bias than non-metric\napproaches when training data is limited in the multi-goal reinforcement\nlearning setting.\n

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.030
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.005
Threshold uncertainty score0.020

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.030
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.003
Scholarly communication0.0020.008
Open science0.0030.005
Research integrity0.0020.005
Insufficient payload (model declined to judge)0.0050.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.306
GPT teacher head0.257
Teacher spread0.049 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations4
Published2020
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicAdvanced Graph Neural NetworksFrench-language works237,207