MétaCan
Menu
Back to cohort
Record W4410086631 · doi:10.1109/tmc.2025.3567179

Mixture-of-Experts as Continual Knowledge Adapter for Mobile Vision Understanding

2025· article· en· W4410086631 on OpenAlexaff
Bicheng Guo, Conghao Zhou, Shibo He, Jiming Chen, Xuemin Shen

Bibliographic record

VenueIEEE Transactions on Mobile Computing · 2025
Typearticle
Languageen
FieldComputer Science
TopicImage Retrieval and Classification Techniques
Canadian institutionsUniversity of Waterloo
FundersNational Natural Science Foundation of China
KeywordsComputer scienceAdapter (computing)Mobile computingMobile telephonyHuman–computer interactionMultimediaComputer securityTelecommunicationsMobile radioOperating system

Abstract

fetched live from OpenAlex

Continual machine learning in the context of limited computational resources and data availability is critical in the connected digital world. Current intelligent applications predominantly rely on deep learning models requiring labor/computation-intensive training. These models often struggle to adapt effectively to new data while preserving performance on previously learned knowledge. In this paper, we introduce a lightweight method for continual knowledge adaptation that can address these challenges. To prevent disruption of the existing services, we propose a Mixture-of-Experts (MoE) adapter that integrates seamlessly with the existing vision model to encode new data. The weights of the original model are kept fixed during the adaptation process, ensuring the preservation of previously learned knowledge. The MoE technique enables scaling up the parameters of the adapter while maintaining a relatively low computation, making it fit for constrained devices in mobile computation scenarios. Furthermore, to enhance learning efficiency and accelerate convergence with new data, we implement a knowledge fusion mechanism that facilitates interaction between the existing knowledge and the information extracted from new data. The timing of employing the fusion module is further investigated. We find that it is conducive in scenarios where the task's performance requirements are enhanced. The MoE adapter and knowledge fusion module are integrated at each stage with minimal trainable parameters, efficiently optimizing resource usage. Extensive experiments and ablation studies validate the effectiveness of the proposed method. Specifically, the proposed method prevents an accuracy drop of 43.02% on the previous data compared to the continual train method, while achieving an accuracy of 44.81% on the new data, which is even 0.34% higher than fully training a new model.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.977
Threshold uncertainty score0.725

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.025
GPT teacher head0.329
Teacher spread0.304 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
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

Citations2
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Mobile ComputingSame topicImage Retrieval and Classification TechniquesFrench-language works237,207