The Geometry of Distributed Representations for Better Alignment, Attenuated Bias, and Improved Interpretability

• URL: http://arxiv.org/abs/2011.12465v1
• Date: Wed, 25 Nov 2020 01:04:11 GMT
• Title: The Geometry of Distributed Representations for Better Alignment, Attenuated Bias, and Improved Interpretability
• Authors: Sunipa Dev
• Abstract summary: High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in machine learning and data mining. These representations have different degrees of interpretability, with efficient distributed representations coming at the cost of the loss of feature to dimension mapping. Its effects are seen in many representations and tasks, one particularly problematic one being in language representations where the societal biases, learned from underlying data, are captured and occluded in unknown dimensions and subspaces. This work addresses some of these problems pertaining to the transparency and interpretability of such representations.
• Score: 9.215513608145994
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in different paradigms of machine learning and data mining. These representations have different degrees of interpretability, with efficient distributed representations coming at the cost of the loss of feature to dimension mapping. This implies that there is obfuscation in the way concepts are captured in these embedding spaces. Its effects are seen in many representations and tasks, one particularly problematic one being in language representations where the societal biases, learned from underlying data, are captured and occluded in unknown dimensions and subspaces. As a result, invalid associations (such as different races and their association with a polar notion of good versus bad) are made and propagated by the representations, leading to unfair outcomes in different tasks where they are used. This work addresses some of these problems pertaining to the transparency and interpretability of such representations. A primary focus is the detection, quantification, and mitigation of socially biased associations in language representation.

Related papers

• Balancing the Scales: Enhancing Fairness in Facial Expression Recognition with Latent Alignment [5.784550537553534]
  This workleverages representation learning based on latent spaces to mitigate bias in facial expression recognition systems. It also enhances a deep learning model's fairness and overall accuracy.
  arXiv  Detail & Related papers  (2024-10-25T10:03:10Z)
• The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication [1.3499500088995464]
  We assess the representational alignment between agent image representations and agent representations and input images. We identify a strong relationship between inter-agent alignment and topographic similarity, a common metric for compositionality. Our findings emphasise the key role representational alignment plays in simulations of language emergence.
  arXiv  Detail & Related papers  (2024-07-25T11:29:27Z)
• Explaining Representation Learning with Perceptual Components [14.10876324116018]
  Self-supervised models create representation spaces that lack clear semantic meaning. We introduce a novel method to analyze representation spaces using three key perceptual components: color, shape, and texture. Our approach enhances the interpretability of the representation space, offering explanations that resonate with human visual perception.
  arXiv  Detail & Related papers  (2024-06-11T04:08:37Z)
• Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation [59.138470433237615]
  We introduce statistical metrics that quantify both the linguistic and visual skew of a dataset for relational learning. We show that systematically controlled metrics are strongly predictive of generalization performance. This work informs an important direction towards quality-enhancing the data diversity or balance to scaling up the absolute size.
  arXiv  Detail & Related papers  (2024-03-25T03:18:39Z)
• Intervention Lens: from Representation Surgery to String Counterfactuals [106.98481791980367]
  Interventions targeting the representation space of language models (LMs) have emerged as an effective means to influence model behavior. We give a method to convert representation counterfactuals into string counterfactuals. The resulting counterfactuals can be used to mitigate bias in classification through data augmentation.
  arXiv  Detail & Related papers  (2024-02-17T18:12:02Z)
• What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary [68.77983831618685]
  We propose to interpret the vector representations produced by dual encoders by projecting them into the model's vocabulary space. We show that the resulting projections contain rich semantic information, and draw connection between them and sparse retrieval.
  arXiv  Detail & Related papers  (2022-12-20T16:03:25Z)
• Latent Topology Induction for Understanding Contextualized Representations [84.7918739062235]
  We study the representation space of contextualized embeddings and gain insight into the hidden topology of large language models. We show there exists a network of latent states that summarize linguistic properties of contextualized representations.
  arXiv  Detail & Related papers  (2022-06-03T11:22:48Z)
• High-dimensional distributed semantic spaces for utterances [0.2907403645801429]
  This paper describes a model for high-dimensional representation for utterance and text level data. It is based on a mathematically principled and behaviourally plausible approach to representing linguistic information. The paper shows how the implemented model is able to represent a broad range of linguistic features in a common integral framework of fixed dimensionality.
  arXiv  Detail & Related papers  (2021-04-01T12:09:47Z)
• Interpretable Representations in Explainable AI: From Theory to Practice [7.031336702345381]
  Interpretable representations are the backbone of many explainers that target black-box predictive systems. We study properties of interpretable representations that encode presence and absence of human-comprehensible concepts.
  arXiv  Detail & Related papers  (2020-08-16T21:44:03Z)
• Contrastive Examples for Addressing the Tyranny of the Majority [83.93825214500131]
  We propose to create a balanced training dataset, consisting of the original dataset plus new data points in which the group memberships are intervened. We show that current generative adversarial networks are a powerful tool for learning these data points, called contrastive examples.
  arXiv  Detail & Related papers  (2020-04-14T14:06:44Z)
• Fairness by Learning Orthogonal Disentangled Representations [50.82638766862974]
  We propose a novel disentanglement approach to invariant representation problem. We enforce the meaningful representation to be agnostic to sensitive information by entropy. The proposed approach is evaluated on five publicly available datasets.
  arXiv  Detail & Related papers  (2020-03-12T11:09:15Z)

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.