Learning to Help in Multi-Class Settings

• URL: http://arxiv.org/abs/2501.13810v1
• Date: Thu, 23 Jan 2025 16:32:01 GMT
• Title: Learning to Help in Multi-Class Settings
• Authors: Yu Wu, Yansong Li, Zeyu Dong, Nitya Sathyavageeswaran, Anand D. Sarwate,
• Abstract summary: A hybrid system can be established by augmenting the local model with a server-side model. The proposed Learning to Help (L2H) model trains a server model given a fixed local (client) model. In both L2D and L2H, the training includes learning a rejector at the client to determine when to query the server.
• Score: 11.972877486351987
• License:
• Abstract: Deploying complex machine learning models on resource-constrained devices is challenging due to limited computational power, memory, and model retrainability. To address these limitations, a hybrid system can be established by augmenting the local model with a server-side model, where samples are selectively deferred by a rejector and then sent to the server for processing. The hybrid system enables efficient use of computational resources while minimizing the overhead associated with server usage. The recently proposed Learning to Help (L2H) model trains a server model given a fixed local (client) model, differing from the Learning to Defer (L2D) framework, which trains the client for a fixed (expert) server. In both L2D and L2H, the training includes learning a rejector at the client to determine when to query the server. In this work, we extend the L2H model from binary to multi-class classification problems and demonstrate its applicability in a number of different scenarios of practical interest in which access to the server may be limited by cost, availability, or policy. We derive a stage-switching surrogate loss function that is differentiable, convex, and consistent with the Bayes rule corresponding to the 0-1 loss for the L2H model. Experiments show that our proposed methods offer an efficient and practical solution for multi-class classification in resource-constrained environments.

Related papers

• Mixture of Attentions For Speculative Decoding [17.344416130742232]
  Speculative decoding (SD) leverages smaller models to efficiently propose future tokens, which are then verified by the Large Language Models in parallel. We identify several limitations of SD models including the lack of on-policyness during training and partial observability. We propose a more grounded architecture for small models by introducing a Mixture of Attentions for SD.
  arXiv  Detail & Related papers  (2024-10-04T10:25:52Z)
• A learning-based solution approach to the application placement problem in mobile edge computing under uncertainty [0.0]
  Placing applications in mobile edge computing servers presents a complex challenge involving many servers, users, and their requests. One of these approaches is machine learning, which emulates optimal solutions for application placement in edge servers. This research aims to provide a more efficient approach for tackling high-dimensional problems and scenarios with uncertainties in mobile edge computing.
  arXiv  Detail & Related papers  (2024-03-17T16:23:00Z)
• When Computing Power Network Meets Distributed Machine Learning: An Efficient Federated Split Learning Framework [6.871107511111629]
  CPN-FedSL is a Federated Split Learning (FedSL) framework over Computing Power Network (CPN) We build a dedicated model to capture the basic settings and learning characteristics (e.g., latency, flow, convergence)
  arXiv  Detail & Related papers  (2023-05-22T12:36:52Z)
• PFSL: Personalized & Fair Split Learning with Data & Label Privacy for thin clients [0.5144809478361603]
  PFSL is a new framework of distributed split learning where a large number of thin clients perform transfer learning in parallel. We implement a lightweight step of personalization of client models to provide high performance for their respective data distributions. Our accuracy far exceeds that of current algorithms SL and is very close to that of centralized learning on several real-life benchmarks.
  arXiv  Detail & Related papers  (2023-03-19T10:38:29Z)
• Architecting Peer-to-Peer Serverless Distributed Machine Learning Training for Improved Fault Tolerance [1.495380389108477]
  Serverless computing is a new paradigm for cloud computing that uses functions as a computational unit. By distributing the workload, distributed machine learning can speed up the training process and allow more complex models to be trained. We propose exploring the use of serverless computing in distributed machine learning training and comparing the performance of P2P architecture with the parameter server architecture.
  arXiv  Detail & Related papers  (2023-02-27T17:38:47Z)
• AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving [53.01646445659089]
  We show that model parallelism can be used for the statistical multiplexing of multiple devices when serving multiple models. We present a novel serving system, AlpaServe, that determines an efficient strategy for placing and parallelizing collections of large deep learning models.
  arXiv  Detail & Related papers  (2023-02-22T21:41:34Z)
• Scalable Collaborative Learning via Representation Sharing [53.047460465980144]
  Federated learning (FL) and Split Learning (SL) are two frameworks that enable collaborative learning while keeping the data private (on device) In FL, each data holder trains a model locally and releases it to a central server for aggregation. In SL, the clients must release individual cut-layer activations (smashed data) to the server and wait for its response (during both inference and back propagation). In this work, we present a novel approach for privacy-preserving machine learning, where the clients collaborate via online knowledge distillation using a contrastive loss.
  arXiv  Detail & Related papers  (2022-11-20T10:49:22Z)
• Switchable Representation Learning Framework with Self-compatibility [50.48336074436792]
  We propose a Switchable representation learning Framework with Self-Compatibility (SFSC) SFSC generates a series of compatible sub-models with different capacities through one training process. SFSC achieves state-of-the-art performance on the evaluated datasets.
  arXiv  Detail & Related papers  (2022-06-16T16:46:32Z)
• Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networks [50.68446003616802]
  Federated learning (FedL) has emerged as a popular technique for distributing model training over a set of wireless devices. We develop parallel successive learning (PSL), which expands the FedL architecture along three dimensions. Our analysis sheds light on the notion of cold vs. warmed up models, and model inertia in distributed machine learning.
  arXiv  Detail & Related papers  (2022-02-07T05:11:01Z)
• A Bayesian Federated Learning Framework with Online Laplace Approximation [144.7345013348257]
  Federated learning allows multiple clients to collaboratively learn a globally shared model. We propose a novel FL framework that uses online Laplace approximation to approximate posteriors on both the client and server side. We achieve state-of-the-art results on several benchmarks, clearly demonstrating the advantages of the proposed method.
  arXiv  Detail & Related papers  (2021-02-03T08:36:58Z)
• Ensemble Distillation for Robust Model Fusion in Federated Learning [72.61259487233214]
  Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. We propose ensemble distillation for model fusion, i.e. training the central classifier through unlabeled data on the outputs of the models from the clients.
  arXiv  Detail & Related papers  (2020-06-12T14:49:47Z)

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.