arXiv:2601. 21579v2 Announce Type: replace-cross Abstract: The success of Hyper-Connections (HC) in neural networks (NN) has also highlighted issues related to training instability and restricted scalability.
arXiv:2609. 02672v1 Announce Type: cross Abstract: Hyper-Connections (HC) replace the single residual stream of a Transformer with $n$ parallel ones, mixing them at every layer with a learned $n \times n$ residual matrix.
The paper introduces Orthogonal Hyper-Connections (oHC), a new approach that replaces the single residual stream of a Transformer with multiple parallel streams mixed by a rotation matrix from the group SO(n). By constraining the mixing matrix to SO(n) and parameterizing it with unit quaternions for four streams, oHC prevents both amplification and attenuation of residuals, maintaining training stability and preserving stream diversity. Experiments show that oHC outperforms the single-stream baseline, manifold-constrained Hyper-Connections, and identity-fixed Hyper-Connections across a wide range of downstream tasks.
The paper introduces Spectral‑Sphere‑Constrained Hyper‑Connections (s²HC), a new method for controlling the residual matrices used in Hyper‑Connections (HC). Unlike previous doubly stochastic constraints that caused identity degeneration, expressivity bottlenecks, and parameterization inefficiencies, s²HC confines these matrices to a spectral norm sphere, restoring flexibility over subdominant spectra and eliminating unstable Sinkhorn‑Knopp iterations. This approach preserves training stability while allowing expressive, non‑degenerate residual matrices.
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:2606. 07574v1 Announce Type: cross Abstract: Manifold-constrained hyper-connections (mHCs) have recently been proposed as a principled extension of hyper-connections, where the residual mixing matrices are constrained to be doubly stochastic via projection onto the Birkhoff polytope.
arXiv:2608. 07851v1 Announce Type: new Abstract: Residual connections rely on a static residual pathway, and are essential for training deep neural networks.
arXiv:2609.21039v1 Announce Type: new Abstract: A pervasive structural pattern in modern deep learning is the linear factorization block: a submodule of the form $W = BA$ in which two parameter matri...
arXiv:2607. 14530v1 Announce Type: new Abstract: Hyper-Connections (HC) expand the residual stream of Transformers into $N$ parallel streams, providing a form of memory scaling beyond model width and depth.
arXiv:2607. 18130v1 Announce Type: new Abstract: Most parameter-efficient finetuning (PEFT) methods adapt weights or activations, thus leaving one of the key Transformer components unchanged: residual connections.
arXiv:2606. 01227v1 Announce Type: new Abstract: Many networks not only support but also rely on transient non-normal amplification, an orders-of-magnitude increase in the activity of an otherwise stable system.
arXiv:2605. 18528v2 Announce Type: replace-cross Abstract: A growing lesson from neural network optimization is that optimizer design should respect how the model is parametrized.
arXiv:2605. 23391v2 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) for coupled multiphysics systems suffer systematic accuracy degradation as inter-equation coupling strengthens.