Rethinking the Bias of Foundation Model under Long-tailed Distribution

• URL: http://arxiv.org/abs/2501.15955v1
• Date: Mon, 27 Jan 2025 11:00:19 GMT
• Title: Rethinking the Bias of Foundation Model under Long-tailed Distribution
• Authors: Jiahao Chen, Bin Qin, Jiangmeng Li, Hao Chen, Bing Su,
• Abstract summary: We find the imbalance biases inherited in foundation models on downstream task as parameter imbalance and data imbalance.<n>During fine-tuning, we observe that parameter imbalance plays a more critical role, while data imbalance can be mitigated using existing re-balancing strategies.<n>We propose a novel backdoor adjustment method that learns the true causal effect between input samples and labels.
• Score: 18.80942166783087
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing methods primarily focus on leveraging knowledge from these models, overlooking the inherent biases introduced by the imbalanced training data they rely on. In this paper, we examine how such imbalances from pre-training affect long-tailed downstream tasks. Specifically, we find the imbalance biases inherited in foundation models on downstream task as parameter imbalance and data imbalance. During fine-tuning, we observe that parameter imbalance plays a more critical role, while data imbalance can be mitigated using existing re-balancing strategies. Moreover, we find that parameter imbalance cannot be effectively addressed by current re-balancing techniques, such as adjusting the logits, during training, unlike data imbalance. To tackle both imbalances simultaneously, we build our method on causal learning and view the incomplete semantic factor as the confounder, which brings spurious correlations between input samples and labels. To resolve the negative effects of this, we propose a novel backdoor adjustment method that learns the true causal effect between input samples and labels, rather than merely fitting the correlations in the data. Notably, we achieve an average performance increase of about $1.67\%$ on each dataset.

Related papers

• Class-Conditional Distribution Balancing for Group Robust Classification [11.525201208566925]
  Spurious correlations that lead models to correct predictions for the wrong reasons pose a critical challenge for robust real-world generalization. We offer a novel perspective by reframing the spurious correlations as imbalances or mismatches in class-conditional distributions. We propose a simple yet effective robust learning method that eliminates the need for both bias annotations and predictions.
  arXiv  Detail & Related papers  (2025-04-24T07:15:53Z)
• Mind the Graph When Balancing Data for Fairness or Robustness [73.03155969727038]
  We define conditions on the training distribution for data balancing to lead to fair or robust models. Our results show that, in many cases, the balanced distribution does not correspond to selectively removing the undesired dependencies. Overall, our results highlight the importance of taking the causal graph into account before performing data balancing.
  arXiv  Detail & Related papers  (2024-06-25T10:16:19Z)
• Gradient Reweighting: Towards Imbalanced Class-Incremental Learning [8.438092346233054]
  Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data. A major challenge of CIL arises when applying to real-world data characterized by non-uniform distribution. We show that this dual imbalance issue causes skewed gradient updates with biased weights in FC layers, thus inducing over/under-fitting and catastrophic forgetting in CIL.
  arXiv  Detail & Related papers  (2024-02-28T18:08:03Z)
• Class-Imbalanced Graph Learning without Class Rebalancing [62.1368829847041]
  Class imbalance is prevalent in real-world node classification tasks and poses great challenges for graph learning models. In this work, we approach the root cause of class-imbalance bias from an topological paradigm. We devise a lightweight topological augmentation framework BAT to mitigate the class-imbalance bias without class rebalancing.
  arXiv  Detail & Related papers  (2023-08-27T19:01:29Z)
• Alleviating the Effect of Data Imbalance on Adversarial Training [26.36714114672729]
  We study adversarial training on datasets that obey the long-tailed distribution. We propose a new adversarial training framework -- Re-balancing Adversarial Training (REAT)
  arXiv  Detail & Related papers  (2023-07-14T07:01:48Z)
• The Effect of Balancing Methods on Model Behavior in Imbalanced Classification Problems [4.370097023410272]
  Imbalanced data poses a challenge in classification as model performance is affected by insufficient learning from minority classes. This study addresses a more challenging aspect of balancing methods - their impact on model behavior. To capture these changes, Explainable Artificial Intelligence tools are used to compare models trained on datasets before and after balancing.
  arXiv  Detail & Related papers  (2023-06-30T22:25:01Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning [103.65758569417702]
  Semi-supervised learning (SSL) has shown great promise in leveraging unlabeled data to improve model performance. We consider a more realistic and challenging setting called imbalanced SSL, where imbalanced class distributions occur in both labeled and unlabeled data. We study a simple yet overlooked baseline -- SimiS -- which tackles data imbalance by simply supplementing labeled data with pseudo-labels.
  arXiv  Detail & Related papers  (2022-11-20T21:18:41Z)
• Robust and Efficient Imbalanced Positive-Unlabeled Learning with Self-supervision [1.5675763601034223]
  We present textitImPULSeS, a unified representation learning framework for underlineImbalanced underlinePositive underlineUnlabeled underlineLearning. We performed different experiments across multiple datasets to show that ImPULSeS is able to halve the error rate of the previous state-of-the-art.
  arXiv  Detail & Related papers  (2022-09-06T12:54:59Z)
• Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification [74.62203971625173]
  Imbalanced data pose challenges for deep learning based classification models. One of the most widely-used approaches for tackling imbalanced data is re-weighting. We propose a novel re-weighting method based on optimal transport (OT) from a distributional point of view.
  arXiv  Detail & Related papers  (2022-08-05T01:23:54Z)
• Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for Imbalanced Classification [11.673344551762822]
  Deep neural networks generally perform poorly with datasets that suffer from quantity imbalance and classification difficulty imbalance between different classes. A phased progressive learning schedule was proposed for smoothly transferring the training emphasis from representation learning to upper classifier training. Our code will be open source soon.
  arXiv  Detail & Related papers  (2022-05-24T14:46:39Z)
• Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models [50.537859423741644]
  Training a model on an imbalanced dataset can introduce unique challenges to the learning problem. We look deeper into the internal units of neural networks to observe how handling data imbalance affects the learned features.
  arXiv  Detail & Related papers  (2022-04-04T09:38:38Z)
• Counterfactual Representation Learning with Balancing Weights [74.67296491574318]
  Key to causal inference with observational data is achieving balance in predictive features associated with each treatment type. Recent literature has explored representation learning to achieve this goal. We develop an algorithm for flexible, scalable and accurate estimation of causal effects.
  arXiv  Detail & Related papers  (2020-10-23T19:06:03Z)
• On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks [94.23884467360521]
  We show that state-of-the art models trained on QQP and WikiQA each have only $2.4%$ average precision when evaluated on realistically imbalanced test data. By creating balanced training data with more informative negative examples, active learning greatly improves average precision to $32.5%$ on QQP and $20.1%$ on WikiQA.
  arXiv  Detail & Related papers  (2020-10-10T21:56:27Z)
• Long-Tailed Recognition Using Class-Balanced Experts [128.73438243408393]
  We propose an ensemble of class-balanced experts that combines the strength of diverse classifiers. Our ensemble of class-balanced experts reaches results close to state-of-the-art and an extended ensemble establishes a new state-of-the-art on two benchmarks for long-tailed recognition.
  arXiv  Detail & Related papers  (2020-04-07T20:57:44Z)
• Precise Tradeoffs in Adversarial Training for Linear Regression [55.764306209771405]
  We provide a precise and comprehensive understanding of the role of adversarial training in the context of linear regression with Gaussian features. We precisely characterize the standard/robust accuracy and the corresponding tradeoff achieved by a contemporary mini-max adversarial training approach. Our theory for adversarial training algorithms also facilitates the rigorous study of how a variety of factors (size and quality of training data, model overparametrization etc.) affect the tradeoff between these two competing accuracies.
  arXiv  Detail & Related papers  (2020-02-24T19:01:47Z)

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.