arXiv:2606. 14022v3 Announce Type: replace Abstract: Graph neural networks (GNNs) are widely used to learn node-selection policies on graphs, and most stack graph attention (GAT) blocks with LayerNorm.
arXiv:2606. 14022v1 Announce Type: new Abstract: LayerNorm-based GNNs routinely erase the topology signals (degree, centrality, $k$-core) that node-selection policies should depend on, but the literature has not located where in the residual block the erasure happens.
arXiv:2604. 17324v2 Announce Type: replace-cross Abstract: Global self-attention drives modern graph transformers, yet the softmax at its core imposes a structural constraint rarely examined directly: every attention row is non-negative and sums to one, so each per-head output is a mass-conserving convex combination of value vectors.
arXiv:2606. 25971v1 Announce Type: new Abstract: Modern neural network training relies on optimizers such as Adam and Muon which act on each weight matrix as a single object.
We investigate how each component of the Transformer feedforward block architecture design determines how much rank survives across depth at initialization. We reinterpret skip connections and normalization, long understood as controlling magnitude, as mechanisms for preserving gradient rank across depth, since the very matrix multiplications and nonlinear activations that make the network expressive also reduce the rank.
arXiv:2607. 14018v1 Announce Type: cross Abstract: We investigate how each component of the Transformer feedforward block architecture design determines how much rank survives across depth at initialization.
arXiv:2607. 21885v1 Announce Type: new Abstract: Coarsening-based training for graph neural networks (GNNs), i.
arXiv:2606. 14476v1 Announce Type: new Abstract: A growing line of work equips large language model (LLM) agents with graph neural networks (GNNs) as callable tools, assuming the agent exercises judgment over when and how much to rely on such a tool.
arXiv:2607. 09967v1 Announce Type: cross Abstract: Many neural networks operations have a multiplicative nature rather than additive: halving or doubling a norm are analogous relatively but require unequal optimization distances when taking linear steps.
arXiv:2608. 02938v1 Announce Type: cross Abstract: Graph attention normalizes neighborhood scores with softmax, the maximum-entropy choice under Shannon statistics.
arXiv:2607. 05017v1 Announce Type: cross Abstract: The performance of deep learning models crucially depends on the settings of hyperparameters like learning rate, initialization scale, and weight decay.
arXiv:2606. 12581v1 Announce Type: cross Abstract: Real-world networks are inherently incomplete, noisy, and dynamically evolving, making it difficult to capture all actors and their relationships.
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).