A Procedural World Generation Framework for Systematic Evaluation of Continual Learning

• URL: http://arxiv.org/abs/2106.02585v1
• Date: Fri, 4 Jun 2021 16:31:43 GMT
• Title: A Procedural World Generation Framework for Systematic Evaluation of Continual Learning
• Authors: Timm Hess, Martin Mundt, Iuliia Pliushch, Visvanathan Ramesh
• Abstract summary: We introduce a computer graphics simulation framework that repeatedly renders only upcoming urban scene fragments. At its core lies a modular parametric generative model with adaptable generative factors.
• Score: 2.599882743586164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data. However, a comprehensive comparison and analysis of limitations remains largely open due to the inaccessibility to suitable datasets. Empirical examination not only varies immensely between individual works, it further currently relies on contrived composition of benchmarks through subdivision and concatenation of various prevalent static vision datasets. In this work, our goal is to bridge this gap by introducing a computer graphics simulation framework that repeatedly renders only upcoming urban scene fragments in an endless real-time procedural world generation process. At its core lies a modular parametric generative model with adaptable generative factors. The latter can be used to flexibly compose data streams, which significantly facilitates a detailed analysis and allows for effortless investigation of various continual learning schemes.

Related papers

• A Practitioner's Guide to Continual Multimodal Pretraining [83.63894495064855]
  Multimodal foundation models serve numerous applications at the intersection of vision and language. To keep models updated, research into continual pretraining mainly explores scenarios with either infrequent, indiscriminate updates on large-scale new data, or frequent, sample-level updates. We introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements.
  arXiv  Detail & Related papers  (2024-08-26T17:59:01Z)
• A Classifier-Free Incremental Learning Framework for Scalable Medical Image Segmentation [6.591403935303867]
  We introduce a novel segmentation paradigm enabling the segmentation of a variable number of classes within a single classifier-free network. This network is trained using contrastive learning and produces discriminative feature representations that facilitate straightforward interpretation. We demonstrate the flexibility of our method in handling varying class numbers within a unified network and its capacity for incremental learning.
  arXiv  Detail & Related papers  (2024-05-25T19:05:07Z)
• TS-CausalNN: Learning Temporal Causal Relations from Non-linear Non-stationary Time Series Data [0.42156176975445486]
  We propose a Time-Series Causal Neural Network (TS-CausalNN) to discover contemporaneous and lagged causal relations simultaneously. In addition to the simple parallel design, an advantage of the proposed model is that it naturally handles the non-stationarity and non-linearity of the data.
  arXiv  Detail & Related papers  (2024-04-01T20:33:29Z)
• Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning [52.046037471678005]
  We focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories. We propose a novel approach called Dynamic Sub-Graph Distillation (DSGD) for semi-supervised continual learning.
  arXiv  Detail & Related papers  (2023-12-27T04:40:12Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Factor-Assisted Federated Learning for Personalized Optimization with Heterogeneous Data [6.024145412139383]
  Federated learning is an emerging distributed machine learning framework aiming at protecting data privacy. Data in different clients contain both common knowledge and personalized knowledge. We develop a novel personalized federated learning framework for heterogeneous data, which we refer to as FedSplit.
  arXiv  Detail & Related papers  (2023-12-07T13:05:47Z)
• Tackling Computational Heterogeneity in FL: A Few Theoretical Insights [68.8204255655161]
  We introduce and analyse a novel aggregation framework that allows for formalizing and tackling computational heterogeneous data. Proposed aggregation algorithms are extensively analyzed from a theoretical, and an experimental prospective.
  arXiv  Detail & Related papers  (2023-07-12T16:28:21Z)
• Continual Vision-Language Representation Learning with Off-Diagonal Information [112.39419069447902]
  Multi-modal contrastive learning frameworks like CLIP typically require a large amount of image-text samples for training. This paper discusses the feasibility of continual CLIP training using streaming data.
  arXiv  Detail & Related papers  (2023-05-11T08:04:46Z)
• Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review [62.997667081978825]
  This review aims at providing a comprehensive vision of the main state-of-the-art libraries and frameworks for machine learning and data analytics available today. The main simulation, emulation, deployment systems, and testbeds for experimental research on the Edge-to-Cloud Continuum available today are also surveyed.
  arXiv  Detail & Related papers  (2022-04-29T08:06:05Z)
• Towards Federated Bayesian Network Structure Learning with Continuous Optimization [14.779035801521717]
  We present a cross-silo federated learning approach to estimate the structure of Bayesian network. We develop a distributed structure learning method based on continuous optimization.
  arXiv  Detail & Related papers  (2021-10-18T14:36:05Z)

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.