MétaCan
Menu
Back to cohort
Record W4416956238 · doi:10.1145/3769102.3774388

Poster: Leveraging Geo-Spatiality in Geo-Distributed Vector Databases

2025· article· W4416956238 on OpenAlexafffundabout
V. Jean Pineda, Niv Dayan, Eyal de Lara

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicData Management and Algorithms
Canadian institutionsUniversity of Toronto
FundersUniversity of Toronto
KeywordsEmbeddingReplication (statistics)k-nearest neighbors algorithmRouting (electronic design automation)ThroughputWeb query classificationQuery expansionNearest neighbor search

Abstract

fetched live from OpenAlex

Multimodal Retrieval-Augmented Generation (MRAG) systems depend on geo-distributed vector database management systems (GVDBMS) to deliver low-latency multimedia retrieval. Multimedia content that encodes spatial information (e.g., images from Toronto or audio from the Amazon) is produced worldwide. Consequently, GVDBMS face a fundamental trade-off when serving approximate nearest neighbor (ANN) queries: full data replication or broadcast querying. We hypothesize that embeddings produced by pre-trained models exhibit strong geographic locality. By exploiting this non-IID characteristic, query routing can be optimized to reduce cross-region traffic for these datasets and avoid the costs of full replication or query broadcasting. Our evaluation on real-world datasets shows that 42–93% of queries are satisfied by a single geographic partition, and 65–85% require at most half of the partitions to retrieve the top-10 results. Across five datasets (including street-view images and geo-tagged sounds) and multiple embedding models, our approach yields a 2–4× overall system throughput improvement while maintaining 90% accuracy over broadcast querying.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.968
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0010.003
Open science0.0020.005
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

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 head0.036
GPT teacher head0.287
Teacher spread0.251 · 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 teacher head, not a consensus.

Study designOther design
Domainnot available
GenreEmpirical

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

Citations0
Published2025
Admission routes3
Has abstractyes

Explore more

Same topicData Management and AlgorithmsFrench-language works237,207