Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation
Out-of-distribution generalization in neural networks is often hampered by spurious correlations. A common strategy is to mitigate this by removing spurious concepts from the neural network representation of the data. Existing concept-removal methods tend to be overzealous by inadvertently eliminating features associated with the main task of the model, thereby harming model performance. We propose an iterative algorithm that separates spurious from main-task concepts by jointly identifying two low-dimensional orthogonal subspaces in the neural network representation. We evaluate the algorithm on benchmark datasets for computer vision (Waterbirds, CelebA) and natural language processing (MultiNLI), and show that it outperforms existing concept removal methods
Code (0)
등록된 구현이 없습니다.
Tasks
Out-of-Distribution GeneralizationSimilar Papers 제목 키워드 기반
Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation
Concept-based approaches, which aim to identify human-understandable concepts within a model's internal representations, are a promising method for interpreting embeddings from deep neural network models, such as CLIP. W…
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings
Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks. While existing methods are effective at mitigating biases by linear projection, such meth…
Word EmbeddingsDoes SGD really happen in tiny subspaces?
Understanding the training dynamics of deep neural networks is challenging due to their high-dimensional nature and intricate loss landscapes. Recent studies have revealed that, along the training trajectory, the gradien…
Identifying Interpretable Subspaces in Image Representations
We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating croppe…
counterfactualLanguage ModelingLanguage ModellingIdentifying and Disentangling Spurious Features in Pretrained Image Representations
Neural networks employ spurious correlations in their predictions, resulting in decreased performance when these correlations do not hold. Recent works suggest fixing pretrained representations and training a classificat…