A Continual Development Methodology for Large-scale Multitask Dynamic ML
Systems
- URL: http://arxiv.org/abs/2209.07326v1
- Date: Thu, 15 Sep 2022 14:36:17 GMT
- Title: A Continual Development Methodology for Large-scale Multitask Dynamic ML
Systems
- Authors: Andrea Gesmundo
- Abstract summary: The presented work is based on the intuition that defining ML models as modular and unbounded artefacts allows to introduce a novel ML development methodology.
We define a novel method for the generation of multitask ML models as a sequence of extensions and multitasks.
This results in the generation of an ML model capable of jointly solving 124 image classification tasks achieving state of the art quality with improved size and compute cost.
- Score: 2.579908688646812
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The traditional Machine Learning (ML) methodology requires to fragment the
development and experimental process into disconnected iterations whose
feedback is used to guide design or tuning choices. This methodology has
multiple efficiency and scalability disadvantages, such as leading to spend
significant resources into the creation of multiple trial models that do not
contribute to the final solution.The presented work is based on the intuition
that defining ML models as modular and extensible artefacts allows to introduce
a novel ML development methodology enabling the integration of multiple design
and evaluation iterations into the continuous enrichment of a single unbounded
intelligent system. We define a novel method for the generation of dynamic
multitask ML models as a sequence of extensions and generalizations. We first
analyze the capabilities of the proposed method by using the standard ML
empirical evaluation methodology. Finally, we propose a novel continuous
development methodology that allows to dynamically extend a pre-existing
multitask large-scale ML system while analyzing the properties of the proposed
method extensions. This results in the generation of an ML model capable of
jointly solving 124 image classification tasks achieving state of the art
quality with improved size and compute cost.
Related papers
- Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging [75.93960998357812]
Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their capabilities across different tasks and domains.
Current model merging techniques focus on merging all available models simultaneously, with weight matrices-based methods being the predominant approaches.
We propose a training-free projection-based continual merging method that processes models sequentially.
arXiv Detail & Related papers (2025-01-16T13:17:24Z) - Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)
We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.
We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
arXiv Detail & Related papers (2024-12-19T13:25:39Z) - RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks.
Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs.
In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
arXiv Detail & Related papers (2024-10-18T03:45:19Z) - Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation [70.22782550540714]
Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW.
We introduce a Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW.
arXiv Detail & Related papers (2024-08-07T12:42:09Z) - Intuition-aware Mixture-of-Rank-1-Experts for Parameter Efficient Finetuning [50.73666458313015]
Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications.
MoE has been emerged as a promising solution with its sparse architecture for effective task decoupling.
Intuition-MoR1E achieves superior efficiency and 2.15% overall accuracy improvement across 14 public datasets.
arXiv Detail & Related papers (2024-04-13T12:14:58Z) - Process Modeling With Large Language Models [42.0652924091318]
This paper explores the integration of Large Language Models (LLMs) into process modeling.
We propose a framework that leverages LLMs for the automated generation and iterative refinement of process models.
Preliminary results demonstrate the framework's ability to streamline process modeling tasks.
arXiv Detail & Related papers (2024-03-12T11:27:47Z) - Model Composition for Multimodal Large Language Models [71.5729418523411]
We propose a new paradigm through the model composition of existing MLLMs to create a new model that retains the modal understanding capabilities of each original model.
Our basic implementation, NaiveMC, demonstrates the effectiveness of this paradigm by reusing modality encoders and merging LLM parameters.
arXiv Detail & Related papers (2024-02-20T06:38:10Z) - Challenges and opportunities for machine learning in multiscale
computational modeling [0.0]
Solving for complex multiscale systems remains computationally onerous due to the high dimensionality of the solution space.
Machine learning (ML) has emerged as a promising solution that can either serve as a surrogate for, accelerate or augment traditional numerical methods.
This paper provides a perspective on the opportunities and challenges of using ML for complex multiscale modeling and simulation.
arXiv Detail & Related papers (2023-03-22T02:04:39Z) - A Multi-Agent Framework for the Asynchronous and Collaborative Extension
of Multitask ML Systems [2.579908688646812]
Tradition ML development methodology does not enable a large number of contributors to work collectively on the creation and extension of a shared intelligent system.
We present a multi-agent framework for collaborative and asynchronous extension of dynamic large-scale multitask intelligent systems.
arXiv Detail & Related papers (2022-09-29T13:02:58Z) - Manifold for Machine Learning Assurance [9.594432031144716]
We propose an analogous approach for machine-learning (ML) systems using an ML technique that extracts from the high-dimensional training data implicitly describing the required system.
It is then harnessed for a range of quality assurance tasks such as test adequacy measurement, test input generation, and runtime monitoring of the target ML system.
Preliminary experiments establish that the proposed manifold-based approach, for test adequacy drives diversity in test data, for test generation yields fault-revealing yet realistic test cases, and for runtime monitoring provides an independent means to assess trustability of the target system's output.
arXiv Detail & Related papers (2020-02-08T11:39:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.