Drinking from a Firehose: Continual Learning with Web-scale Natural Language

• URL: http://arxiv.org/abs/2007.09335v2
• Date: Mon, 2 Nov 2020 02:34:21 GMT
• Title: Drinking from a Firehose: Continual Learning with Web-scale Natural Language
• Authors: Hexiang Hu, Ozan Sener, Fei Sha, Vladlen Koltun
• Abstract summary: We study a natural setting for continual learning on a massive scale. We collect massive datasets of Twitter posts. We present a rigorous evaluation of continual learning algorithms on an unprecedented scale.
• Score: 109.80198763438248
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning systems will interact with humans, with each other, and with the physical world through time -- and continue to learn and adapt as they do. An important open problem for continual learning is a large-scale benchmark that enables realistic evaluation of algorithms. In this paper, we study a natural setting for continual learning on a massive scale. We introduce the problem of personalized online language learning (POLL), which involves fitting personalized language models to a population of users that evolves over time. To facilitate research on POLL, we collect massive datasets of Twitter posts. These datasets, Firehose10M and Firehose100M, comprise 100 million tweets, posted by one million users over six years. Enabled by the Firehose datasets, we present a rigorous evaluation of continual learning algorithms on an unprecedented scale. Based on this analysis, we develop a simple algorithm for continual gradient descent (ConGraD) that outperforms prior continual learning methods on the Firehose datasets as well as earlier benchmarks. Collectively, the POLL problem setting, the Firehose datasets, and the ConGraD algorithm enable a complete benchmark for reproducible research on web-scale continual learning.

Related papers

• Continual Learning for Multimodal Data Fusion of a Soft Gripper [1.0589208420411014]
  A model trained on one data modality often fails when tested with a different modality. We introduce a continual learning algorithm capable of incrementally learning different data modalities. We evaluate the algorithm's effectiveness on a challenging custom multimodal dataset.
  arXiv  Detail & Related papers  (2024-09-20T09:53:27Z)
• Continual Learning on Graphs: Challenges, Solutions, and Opportunities [72.7886669278433]
  We provide a comprehensive review of existing continual graph learning (CGL) algorithms. We compare methods with traditional continual learning techniques and analyze the applicability of the traditional continual learning techniques to forgetting tasks. We will maintain an up-to-date repository featuring a comprehensive list of accessible algorithms.
  arXiv  Detail & Related papers  (2024-02-18T12:24:45Z)
• Continual Learning with Deep Streaming Regularized Discriminant Analysis [0.0]
  We propose a streaming version of regularized discriminant analysis as a solution to this challenge. We combine our algorithm with a convolutional neural network and demonstrate that it outperforms both batch learning and existing streaming learning algorithms.
  arXiv  Detail & Related papers  (2023-09-15T12:25:42Z)
• How Efficient Are Today's Continual Learning Algorithms? [31.120016345185217]
  Supervised continual learning involves updating a deep neural network (DNN) from an ever-growing stream of labeled data. One of the major motivations behind continual learning is being able to efficiently update a network with new information, rather than retraining from scratch on the training dataset as it grows over time. Here, we study recent methods for incremental class learning and illustrate that many are highly inefficient in terms of compute, memory, and storage.
  arXiv  Detail & Related papers  (2023-03-29T18:52:10Z)
• NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research [96.53307645791179]
  We introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks.
  arXiv  Detail & Related papers  (2022-11-15T18:57:46Z)
• Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data [101.6195176510611]
  "Online" continual learning enables evaluating both information retention and online learning efficacy. In online continual learning, each incoming small batch of data is first used for testing and then added to the training set, making the problem truly online. We introduce a new benchmark for online continual visual learning that exhibits large scale and natural distribution shifts.
  arXiv  Detail & Related papers  (2021-08-20T06:17:20Z)
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation [64.43440450794495]
  We conduct an extensive study of six offline learning algorithms for robot manipulation. Our study analyzes the most critical challenges when learning from offline human data. We highlight opportunities for learning from human datasets.
  arXiv  Detail & Related papers  (2021-08-06T20:48:30Z)
• Deploying Lifelong Open-Domain Dialogue Learning [48.12600947313494]
  In this work, we build and deploy a role-playing game, whereby human players converse with learning agents situated in an open-domain fantasy world. We show that by training models on the conversations they have with humans in the game the models progressively improve, as measured by automatic metrics and online engagement scores. This learning is shown to be more efficient than crowdsourced data when applied to conversations with real users, as well as being far cheaper to collect.
  arXiv  Detail & Related papers  (2020-08-18T17:57:26Z)

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.