arXiv Machine Learning
Jul 9
Adversarial Rademacher Complexity of Deep Neural Networks
arXiv:2211. 14966v2 Announce Type: replace Abstract: Deep neural networks (DNNs) are highly vulnerable to adversarial attacks.
On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry
arXiv:2510. 10101v4 Announce Type: replace Abstract: Understanding the interplay between generalization, expressivity, and the geometry of the input space is a central challenge in graph learning.
Related stories
arXiv Machine Learning
Jun 2
Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models
arXiv:2503. 07325v2 Announce Type: replace Abstract: Understanding and certifying the behavior of modern deep neural networks remains a fundamental challenge in reliable machine learning.
arXiv Machine Learning
Jul 8
Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity
arXiv:2607. 05546v1 Announce Type: cross Abstract: We develop a unified function space theory of deep fully connected neural networks.
Hugging Face Trending Papers
Jun 11
Understanding Truncated Positional Encodings for Graph Neural Networks
Positional encodings (PEs) enhance the power of graph neural networks (GNNs), both theoretically and empirically. Two of the most popular families of PEs - spectral (e.
arXiv Machine Learning
Jun 30
Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks
arXiv:2603. 14846v3 Announce Type: replace Abstract: We define an information-complexity property for aggregation functions, capturing a vast range of practical aggregations, and prove that any Message-Passing Graph Neural Network (MP-GNN) model with such aggregations induces only a polynomial number of equivalence classes on all graphs - while the number of non-isomorphic graphs is super-exponential (in number of vertices).
arXiv Machine Learning
Jul 9
Any-Dimensional Learning by Sampling
arXiv:2607. 07680v1 Announce Type: cross Abstract: Many machine learning models are defined for inputs of different sizes, such as point clouds containing different numbers of points, sequences of tokens of different lengths, and graphs on different numbers of nodes.
arXiv Machine Learning
Jun 2
Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization
arXiv:2505. 18113v2 Announce Type: replace Abstract: Training quantized neural networks requires addressing the non-differentiable and discrete nature of the underlying optimization problem.
arXiv AI
Jun 18
Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers
arXiv:2503. 01805v3 Announce Type: replace-cross Abstract: Transformers have revolutionized the field of machine learning.
arXiv AI
Jun 8
Learning to Execute Graph Algorithms Exactly with Graph Neural Networks
arXiv:2601. 23207v2 Announce Type: replace-cross Abstract: Understanding what graph neural networks can learn, especially their ability to learn to execute algorithms, remains a central theoretical challenge.
arXiv Machine Learning
Jul 7
Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration
arXiv:2606. 12913v2 Announce Type: replace Abstract: The rapid growth of modern training datasets has significantly increased computational cost, motivating dataset pruning~(DP) methods which retain only a subset of informative samples to reduce training cost.
arXiv AI
Jul 21
mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks
arXiv:2601. 02451v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) suffer from over-smoothing in deep architectures and expressiveness bounded by the 1-Weisfeiler-Leman (1-WL) test.
arXiv Machine Learning
Jul 21
A Weisfeiler-Leman Characterization of Global-Attention Graph Transformers for Mixed-Integer Linear Programs
arXiv:2607. 17570v1 Announce Type: new Abstract: Graph foundation models (GFMs) with global attention are increasingly used to represent mixed-integer linear programs (MILPs), aiming to capture structure beyond the locality of standard graph neural networks.