Predicting What You Already Know Helps: Provable Self-Supervised Learning

• URL: http://arxiv.org/abs/2008.01064v2
• Date: Sun, 14 Nov 2021 04:26:31 GMT
• Title: Predicting What You Already Know Helps: Provable Self-Supervised Learning
• Authors: Jason D. Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo
• Abstract summary: Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data. We show a mechanism exploiting the statistical connections between certain em reconstruction-based pretext tasks that guarantee to learn a good representation. We prove the linear layer yields small approximation error even for complex ground truth function class.
• Score: 60.27658820909876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data to learn useful semantic representations. These pretext tasks are created solely using the input features, such as predicting a missing image patch, recovering the color channels of an image from context, or predicting missing words in text; yet predicting this \textit{known} information helps in learning representations effective for downstream prediction tasks. We posit a mechanism exploiting the statistical connections between certain {\em reconstruction-based} pretext tasks that guarantee to learn a good representation. Formally, we quantify how the approximate independence between the components of the pretext task (conditional on the label and latent variables) allows us to learn representations that can solve the downstream task by just training a linear layer on top of the learned representation. We prove the linear layer yields small approximation error even for complex ground truth function class and will drastically reduce labeled sample complexity. Next, we show a simple modification of our method leads to nonlinear CCA, analogous to the popular SimSiam algorithm, and show similar guarantees for nonlinear CCA.

Related papers

• RanDumb: A Simple Approach that Questions the Efficacy of Continual Representation Learning [68.42776779425978]
  We show that existing online continually trained deep networks produce inferior representations compared to a simple pre-defined random transforms. We then train a simple linear classifier on top without storing any exemplars, processing one sample at a time in an online continual learning setting. Our study reveals the significant limitations of representation learning, particularly in low-exemplar and online continual learning scenarios.
  arXiv  Detail & Related papers  (2024-02-13T22:07:29Z)
• Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior [14.232144691524528]
  Recent Vision-Language Pretrained models have become the backbone for many downstream tasks. MLE training can lead the context vector to over-fit dominant image features in the training data. This paper presents a Bayesian-based framework of prompt learning, which could alleviate the overfitting issues on few-shot learning application.
  arXiv  Detail & Related papers  (2024-01-09T10:15:59Z)
• Mixture of Self-Supervised Learning [2.191505742658975]
  Self-supervised learning works by using a pretext task which will be trained on the model before being applied to a specific task. Previous studies have only used one type of transformation as a pretext task. This raises the question of how it affects if more than one pretext task is used and to use a gating network to combine all pretext tasks.
  arXiv  Detail & Related papers  (2023-07-27T14:38:32Z)
• Is Cross-modal Information Retrieval Possible without Training? [4.616703548353372]
  We take a simple mapping computed from the least squares and singular value decomposition (SVD) for a solution to the Procrustes problem. That is, given information in one modality such as text, the mapping helps us locate a semantically equivalent data item in another modality such as image. Using off-the-shelf pretrained deep learning models, we have experimented the aforementioned simple cross-modal mappings in tasks of text-to-image and image-to-text retrieval.
  arXiv  Detail & Related papers  (2023-04-20T02:36:18Z)
• The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning [32.15608637930748]
  We show that there exists a trade-off between the two desiderata so that one may not be able to achieve both simultaneously. We provide analysis using a theoretical data model and show that, while more diverse pre-training data result in more diverse features for different tasks, it puts less emphasis on task-specific features.
  arXiv  Detail & Related papers  (2023-02-28T22:14:33Z)
• Fine-Grained Visual Entailment [51.66881737644983]
  We propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image. Unlike prior work, our method is inherently explainable and makes logical predictions at different levels of granularity. We evaluate our method on a new dataset of manually annotated knowledge elements and show that our method achieves 68.18% accuracy at this challenging task.
  arXiv  Detail & Related papers  (2022-03-29T16:09:38Z)
• Fair Interpretable Learning via Correction Vectors [68.29997072804537]
  We propose a new framework for fair representation learning centered around the learning of "correction vectors" The corrections are then simply summed up to the original features, and can therefore be analyzed as an explicit penalty or bonus to each feature. We show experimentally that a fair representation learning problem constrained in such a way does not impact performance.
  arXiv  Detail & Related papers  (2022-01-17T10:59:33Z)
• DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting [91.56988987393483]
  We present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP. Specifically, we convert the original image-text matching problem in CLIP to a pixel-text matching problem and use the pixel-text score maps to guide the learning of dense prediction models. Our method is model-agnostic, which can be applied to arbitrary dense prediction systems and various pre-trained visual backbones.
  arXiv  Detail & Related papers  (2021-12-02T18:59:32Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

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.