Recommendation of data-free class-incremental learning algorithms by simulating future data

• URL: http://arxiv.org/abs/2403.18132v1
• Date: Tue, 26 Mar 2024 22:26:39 GMT
• Title: Recommendation of data-free class-incremental learning algorithms by simulating future data
• Authors: Eva Feillet, Adrian Popescu, Céline Hudelot,
• Abstract summary: Class-incremental learning deals with sequential data streams composed of batches of classes. We introduce an algorithm recommendation method that simulates the future data stream. We evaluate recent algorithms on the simulated stream and recommend the one which performs best in the user-defined incremental setting.
• Score: 10.309079388745753
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Class-incremental learning deals with sequential data streams composed of batches of classes. Various algorithms have been proposed to address the challenging case where samples from past classes cannot be stored. However, selecting an appropriate algorithm for a user-defined setting is an open problem, as the relative performance of these algorithms depends on the incremental settings. To solve this problem, we introduce an algorithm recommendation method that simulates the future data stream. Given an initial set of classes, it leverages generative models to simulate future classes from the same visual domain. We evaluate recent algorithms on the simulated stream and recommend the one which performs best in the user-defined incremental setting. We illustrate the effectiveness of our method on three large datasets using six algorithms and six incremental settings. Our method outperforms competitive baselines, and performance is close to that of an oracle choosing the best algorithm in each setting. This work contributes to facilitate the practical deployment of incremental learning.

Related papers

• Triangle and Four Cycle Counting with Predictions in Graph Streams [59.05440236993604]
  We propose data-driven one-pass streaming algorithms for estimating the number of triangles and four cycles. We use a trained oracle that can predict certain properties of the stream elements to improve on prior "classical" algorithms. Our methodology expands upon prior work on "classical" streaming algorithms, as previous multi-pass and random order streaming algorithms can be seen as special cases.
  arXiv  Detail & Related papers  (2022-03-17T19:26:00Z)
• Machine Learning for Online Algorithm Selection under Censored Feedback [71.6879432974126]
  In online algorithm selection (OAS), instances of an algorithmic problem class are presented to an agent one after another, and the agent has to quickly select a presumably best algorithm from a fixed set of candidate algorithms. For decision problems such as satisfiability (SAT), quality typically refers to the algorithm's runtime. In this work, we revisit multi-armed bandit algorithms for OAS and discuss their capability of dealing with the problem. We adapt them towards runtime-oriented losses, allowing for partially censored data while keeping a space- and time-complexity independent of the time horizon.
  arXiv  Detail & Related papers  (2021-09-13T18:10:52Z)
• Probabilistic Active Learning for Active Class Selection [3.6471065658293043]
  In machine learning, active class selection (ACS) algorithms aim to actively select a class and ask the oracle to provide an instance for that class. We propose a new algorithm (PAL-ACS) that transforms the ACS problem into an active learning task by introducing pseudo instances.
  arXiv  Detail & Related papers  (2021-08-09T09:20:19Z)
• Algorithm Selection on a Meta Level [58.720142291102135]
  We introduce the problem of meta algorithm selection, which essentially asks for the best way to combine a given set of algorithm selectors. We present a general methodological framework for meta algorithm selection as well as several concrete learning methods as instantiations of this framework.
  arXiv  Detail & Related papers  (2021-07-20T11:23:21Z)
• A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data [0.0]
  Counterfactual explanations are viewed as an effective way to explain machine learning predictions. There are already dozens of algorithms aiming to generate such explanations. benchmarking study and framework can help practitioners in determining which technique and building blocks most suit their context.
  arXiv  Detail & Related papers  (2021-07-09T21:06:03Z)
• Data-driven Weight Initialization with Sylvester Solvers [72.11163104763071]
  We propose a data-driven scheme to initialize the parameters of a deep neural network. We show that our proposed method is especially effective in few-shot and fine-tuning settings.
  arXiv  Detail & Related papers  (2021-05-02T07:33:16Z)
• Leveraging Benchmarking Data for Informed One-Shot Dynamic Algorithm Selection [0.9281671380673306]
  A key challenge in the application of evolutionary algorithms is the selection of an algorithm instance that best suits the problem at hand. We analyze in this work how such prior performance data can be used to infer informed dynamic algorithm selection schemes for the solution of pseudo-Boolean optimization problems.
  arXiv  Detail & Related papers  (2021-02-12T12:27:02Z)
• Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms [19.65665942630067]
  Active learning (AL) algorithms may achieve better performance with fewer data because the model guides the data selection process. There is little study on what the optimal AL looks like, which would help researchers understand where their models fall short. We present a simulated annealing algorithm to search for this optimal oracle and analyze it for several tasks.
  arXiv  Detail & Related papers  (2020-12-29T22:56:42Z)
• Run2Survive: A Decision-theoretic Approach to Algorithm Selection based on Survival Analysis [75.64261155172856]
  survival analysis (SA) naturally supports censored data and offers appropriate ways to use such data for learning distributional models of algorithm runtime. We leverage such models as a basis of a sophisticated decision-theoretic approach to algorithm selection, which we dub Run2Survive. In an extensive experimental study with the standard benchmark ASlib, our approach is shown to be highly competitive and in many cases even superior to state-of-the-art AS approaches.
  arXiv  Detail & Related papers  (2020-07-06T15:20:17Z)
• Extreme Algorithm Selection With Dyadic Feature Representation [78.13985819417974]
  We propose the setting of extreme algorithm selection (XAS) where we consider fixed sets of thousands of candidate algorithms. We assess the applicability of state-of-the-art AS techniques to the XAS setting and propose approaches leveraging a dyadic feature representation.
  arXiv  Detail & Related papers  (2020-01-29T09:40:58Z)

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.