Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research

• URL: http://arxiv.org/abs/2403.08438v2
• Date: Tue, 19 Mar 2024 10:54:22 GMT
• Title: Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research
• Authors: Tobias Hille, Maximilian Stubbemann, Tom Hanika,
• Abstract summary: Building on these efforts we turn towards another critical challenge in machine learning, namely the curse of dimensionality. Using the closely linked concept of intrinsic dimension we investigate to which the used machine learning models are influenced by the extend dimension of the data sets they are trained on.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Difficulties in replication and reproducibility of empirical evidences in machine learning research have become a prominent topic in recent years. Ensuring that machine learning research results are sound and reliable requires reproducibility, which verifies the reliability of research findings using the same code and data. This promotes open and accessible research, robust experimental workflows, and the rapid integration of new findings. Evaluating the degree to which research publications support these different aspects of reproducibility is one goal of the present work. For this we introduce an ontology of reproducibility in machine learning and apply it to methods for graph neural networks. Building on these efforts we turn towards another critical challenge in machine learning, namely the curse of dimensionality, which poses challenges in data collection, representation, and analysis, making it harder to find representative data and impeding the training and inference processes. Using the closely linked concept of geometric intrinsic dimension we investigate to which extend the used machine learning models are influenced by the intrinsic dimension of the data sets they are trained on.

Related papers

• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• Mechanistic Neural Networks for Scientific Machine Learning [58.99592521721158]
  We present Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences. It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations. Central to our approach is a novel Relaxed Linear Programming solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs.
  arXiv  Detail & Related papers  (2024-02-20T15:23:24Z)
• Innovation and Word Usage Patterns in Machine Learning [1.3812010983144802]
  We identify pivotal themes and fundamental concepts that have emerged within the realm of machine learning. To quantify the novelty and divergence of research contributions, we employ the Kullback-Leibler Divergence metric.
  arXiv  Detail & Related papers  (2023-11-07T00:41:15Z)
• Machine learning assisted exploration for affine Deligne-Lusztig varieties [3.7863170254779335]
  This paper presents a novel, interdisciplinary study that leverages a Machine Learning (ML) assisted framework to explore the geometry of affine Deligne-Lusztig varieties (ADLV) The primary objective is to investigate the nonemptiness pattern, dimension and enumeration of irreducible components of ADLV. We provide a full mathematical proof of a newly identified problem concerning a certain lower bound of dimension.
  arXiv  Detail & Related papers  (2023-08-22T11:12:53Z)
• Homological Neural Networks: A Sparse Architecture for Multivariate Complexity [0.0]
  We develop a novel deep neural network unit characterized by a sparse higher-order graphical architecture built over the homological structure of underlying data. Results demonstrate the advantages of this novel design which can tie or overcome the results of state-of-the-art machine learning and deep learning models using only a fraction of parameters.
  arXiv  Detail & Related papers  (2023-06-27T09:46:16Z)
• A Survey on Few-Shot Class-Incremental Learning [11.68962265057818]
  Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks. This paper provides a comprehensive survey on FSCIL. FSCIL has achieved impressive achievements in various fields of computer vision.
  arXiv  Detail & Related papers  (2023-04-17T10:15:08Z)
• Bridging Machine Learning and Sciences: Opportunities and Challenges [0.0]
  Application of machine learning in sciences has seen exciting advances in recent years. Recently, deep neural nets-based out-of-distribution detection has made great progress for high-dimensional data. We take a critical look at their applicative prospects including data universality, experimental protocols, model robustness, etc.
  arXiv  Detail & Related papers  (2022-10-24T17:54:46Z)
• Research Trends and Applications of Data Augmentation Algorithms [77.34726150561087]
  We identify the main areas of application of data augmentation algorithms, the types of algorithms used, significant research trends, their progression over time and research gaps in data augmentation literature. We expect readers to understand the potential of data augmentation, as well as identify future research directions and open questions within data augmentation research.
  arXiv  Detail & Related papers  (2022-07-18T11:38:32Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• 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)
• Deep Learning for Community Detection: Progress, Challenges and Opportunities [79.26787486888549]
  Article summarizes the contributions of the various frameworks, models, and algorithms in deep neural networks. This article summarizes the contributions of the various frameworks, models, and algorithms in deep neural networks.
  arXiv  Detail & Related papers  (2020-05-17T11:22:11Z)

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.