Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations

• URL: http://arxiv.org/abs/2406.15812v1
• Date: Sat, 22 Jun 2024 10:36:04 GMT
• Title: Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations
• Authors: Lorenzo Basile, Santiago Acevedo, Luca Bortolussi, Fabio Anselmi, Alex Rodriguez,
• Abstract summary: This paper exploits the entanglement between intrinsic dimensionality and correlation to propose a metric that quantifies the correlation. We first validate our method on synthetic data in controlled environments, showcasing its advantages and drawbacks compared to existing techniques. We extend our analysis to large-scale applications in neural network representations.
• Score: 0.4223422932643755
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To gain insight into the mechanisms behind machine learning methods, it is crucial to establish connections among the features describing data points. However, these correlations often exhibit a high-dimensional and strongly nonlinear nature, which makes them challenging to detect using standard methods. This paper exploits the entanglement between intrinsic dimensionality and correlation to propose a metric that quantifies the (potentially nonlinear) correlation between high-dimensional manifolds. We first validate our method on synthetic data in controlled environments, showcasing its advantages and drawbacks compared to existing techniques. Subsequently, we extend our analysis to large-scale applications in neural network representations. Specifically, we focus on latent representations of multimodal data, uncovering clear correlations between paired visual and textual embeddings, whereas existing methods struggle significantly in detecting similarity. Our results indicate the presence of highly nonlinear correlation patterns between latent manifolds.

Related papers

• Detecting Spurious Correlations via Robust Visual Concepts in Real and AI-Generated Image Classification [12.992095539058022]
  We introduce a general-purpose method that efficiently detects potential spurious correlations. The proposed method provides intuitive explanations while eliminating the need for pixel-level annotations. Our method is also suitable for detecting spurious correlations that may propagate to downstream applications originating from generative models.
  arXiv  Detail & Related papers  (2023-11-03T01:12:35Z)
• Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction [121.65152276851619]
  We show that semantic correlations between relations are inherently edge-level and entity-independent. We propose a novel subgraph-based method, namely TACO, to model Topology-Aware COrrelations between relations. To further exploit the potential of RCN, we propose Complete Common Neighbor induced subgraph.
  arXiv  Detail & Related papers  (2023-09-20T08:11:58Z)
• Nonparametric Embeddings of Sparse High-Order Interaction Events [21.758306786651772]
  High-order interaction events are common in real-world applications. We propose Non Embeddings of Sparse High-order interaction events. We develop an efficient, scalable model inference algorithm.
  arXiv  Detail & Related papers  (2022-07-08T01:25:34Z)
• Learning from few examples with nonlinear feature maps [68.8204255655161]
  We explore the phenomenon and reveal key relationships between dimensionality of AI model's feature space, non-degeneracy of data distributions, and the model's generalisation capabilities. The main thrust of our present analysis is on the influence of nonlinear feature transformations mapping original data into higher- and possibly infinite-dimensional spaces on the resulting model's generalisation capabilities.
  arXiv  Detail & Related papers  (2022-03-31T10:36:50Z)
• Learning Neural Causal Models with Active Interventions [83.44636110899742]
  We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting. We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
  arXiv  Detail & Related papers  (2021-09-06T13:10:37Z)
• Leveraging Pre-Images to Discover Nonlinear Relationships in Multivariate Environments [0.0]
  Causal discovery offers a crucial functionality in scientific discovery using artificial intelligence. It became apparent that many real-world temporal observations are nonlinearly related to each other. We show that our method outperforms state-of-the-art causal discovery methods when the observations are restricted by time and are nonlinearly related.
  arXiv  Detail & Related papers  (2021-06-01T22:42:51Z)
• Discovering dependencies in complex physical systems using Neural Networks [0.0]
  A method based on mutual information and deep neural networks is proposed as a versatile framework for discovering non-linear relationships. We demonstrate the application of this method to actual multivariable non-linear dynamical systems.
  arXiv  Detail & Related papers  (2021-01-27T18:59:19Z)
• The Importance of Being Correlated: Implications of Dependence in Joint Spectral Inference across Multiple Networks [4.238478445823]
  Spectral inference on multiple networks is a rapidly-developing subfield of graph statistics. Recent work has demonstrated that joint, or simultaneous, spectral embedding of multiple independent networks can deliver more accurate estimation. We present a generalized omnibus embedding methodology and provide a detailed analysis of this embedding across both independent and correlated networks.
  arXiv  Detail & Related papers  (2020-08-01T03:43:52Z)
• On Disentangled Representations Learned From Correlated Data [59.41587388303554]
  We bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data. We show that systematically induced correlations in the dataset are being learned and reflected in the latent representations. We also demonstrate how to resolve these latent correlations, either using weak supervision during training or by post-hoc correcting a pre-trained model with a small number of labels.
  arXiv  Detail & Related papers  (2020-06-14T12:47:34Z)
• Bayesian Sparse Factor Analysis with Kernelized Observations [67.60224656603823]
  Multi-view problems can be faced with latent variable models. High-dimensionality and non-linear issues are traditionally handled by kernel methods. We propose merging both approaches into single model.
  arXiv  Detail & Related papers  (2020-06-01T14:25:38Z)
• Discovering Nonlinear Relations with Minimum Predictive Information Regularization [67.7764810514585]
  We introduce a novel minimum predictive information regularization method to infer directional relations from time series. Our method substantially outperforms other methods for learning nonlinear relations in synthetic datasets.
  arXiv  Detail & Related papers  (2020-01-07T04:28:00Z)

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.