SG-Blend: Learning an Interpolation Between Improved Swish and GELU for Robust Neural Representations

• URL: http://arxiv.org/abs/2505.23942v1
• Date: Thu, 29 May 2025 18:48:18 GMT
• Title: SG-Blend: Learning an Interpolation Between Improved Swish and GELU for Robust Neural Representations
• Authors: Gaurav Sarkar, Jay Gala, Subarna Tripathi,
• Abstract summary: This work introduces SG-Blend, a novel activation function that blends our proposed SSwish and the established GELU.<n>By adaptively blending these constituent functions via learnable parameters, SG-Blend aims to harness their complementary strengths.
• Score: 8.276787575807392
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The design of activation functions remains a pivotal component in optimizing deep neural networks. While prevailing choices like Swish and GELU demonstrate considerable efficacy, they often exhibit domain-specific optima. This work introduces SG-Blend, a novel activation function that blends our proposed SSwish, a first-order symmetric variant of Swish and the established GELU through dynamic interpolation. By adaptively blending these constituent functions via learnable parameters, SG-Blend aims to harness their complementary strengths: SSwish's controlled non-monotonicity and symmetry, and GELU's smooth, probabilistic profile, to achieve a more universally robust balance between model expressivity and gradient stability. We conduct comprehensive empirical evaluations across diverse modalities and architectures, showing performance improvements across all considered natural language and computer vision tasks and models. These results, achieved with negligible computational overhead, underscore SG-Blend's potential as a versatile, drop-in replacement that consistently outperforms strong contemporary baselines. The code is available at https://anonymous.4open.science/r/SGBlend-6CBC.

Related papers

• Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection [53.45696787935487]
  Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes.<n>In real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID.<n>We propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection.
  arXiv  Detail & Related papers  (2026-02-01T05:54:59Z)
• Learning to Evolve with Convergence Guarantee via Neural Unrolling [37.99564850768798]
  We introduce Learning to Evolve (L2E), a unified bilevel meta-optimization framework.<n>L2E reformulates evolutionary search as a Neural Unrolling process grounded in Krasnosel'skii-Mann (KM) fixed-point theory.<n>Experiments demonstrate the scalability of L2E in high-dimensional spaces and its robust zero-shot generalization across synthetic and real-world control tasks.
  arXiv  Detail & Related papers  (2025-12-12T10:46:25Z)
• Generalized Spherical Neural Operators: Green's Function Formulation [15.000285739440466]
  We propose a general operator-design framework based on the designable spherical Green's function and its harmonic expansion.<n>We develop GSHNet, a hierarchical architecture that combines multi-scale spectral modeling with spherical up-down sampling.<n>Our results position GSNO as a principled and general framework for spherical operator learning, bridging rigorous theory with real-world complexity.
  arXiv  Detail & Related papers  (2025-12-11T15:05:33Z)
• Towards Efficient General Feature Prediction in Masked Skeleton Modeling [59.46799426434277]
  We propose a novel General Feature Prediction framework (GFP) for efficient mask skeleton modeling.<n>Our key innovation is replacing conventional low-level reconstruction with high-level feature prediction that spans from local motion patterns to global semantic representations.
  arXiv  Detail & Related papers  (2025-09-03T18:05:02Z)
• SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR [65.90944188787786]
  Low-rank adaptation (LoRA) is widely used in speech applications, but its state-of-the-art variants, e.g., VeRA, DoRA, PiSSA, and SVFT, are developed mainly for language and vision tasks, with limited validation in speech.<n>This work presents the first comprehensive integration and benchmarking of these PEFT methods within ESPnet.<n>We evaluate all methods on domain-shifted speech recognition tasks, including child speech and dialectal variation, across model scales from 0.1B to 2B.
  arXiv  Detail & Related papers  (2025-09-02T20:51:17Z)
• MISCGrasp: Leveraging Multiple Integrated Scales and Contrastive Learning for Enhanced Volumetric Grasping [15.127239823566194]
  MISCGrasp is a volumetric grasping method that integrates multi-scale feature extraction with contrastive feature enhancement for self-adaptive grasping.<n>We propose a query-based interaction between high-level and low-level features through the Insight Transformer, while the Empower Transformer selectively attends to the highest-level features.<n>Extensive experiments in both simulated and real-world environments demonstrate that MISCGrasp outperforms baseline and variant methods in tabletop decluttering tasks.
  arXiv  Detail & Related papers  (2025-07-03T14:36:45Z)
• HiLAB: A Hybrid Inverse-Design Framework [0.0]
  HiLAB is a new paradigm for inverse design of nanophotonic structures.<n>It addresses multi-functional device design by generating diverse freeform configurations at reduced simulation costs.
  arXiv  Detail & Related papers  (2025-05-23T05:34:56Z)
• RD-UIE: Relation-Driven State Space Modeling for Underwater Image Enhancement [59.364418120895]
  Underwater image enhancement (UIE) is a critical preprocessing step for marine vision applications.<n>We develop a novel relation-driven Mamba framework for effective UIE (RD-UIE)<n>Experiments on underwater enhancement benchmarks demonstrate RD-UIE outperforms the state-of-the-art approach WMamba.
  arXiv  Detail & Related papers  (2025-05-02T12:21:44Z)
• Instruction-Guided Autoregressive Neural Network Parameter Generation [49.800239140036496]
  We propose IGPG, an autoregressive framework that unifies parameter synthesis across diverse tasks and architectures.<n>By autoregressively generating neural network weights' tokens, IGPG ensures inter-layer coherence and enables efficient adaptation across models and datasets.<n>Experiments on multiple datasets demonstrate that IGPG consolidates diverse pretrained models into a single, flexible generative framework.
  arXiv  Detail & Related papers  (2025-04-02T05:50:19Z)
• Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$P Parametrization [66.03821840425539]
  In this paper, we investigate the training dynamics of $L$-layer neural networks using the tensor gradient program (SGD) framework.<n>We show that SGD enables these networks to learn linearly independent features that substantially deviate from their initial values.<n>This rich feature space captures relevant data information and ensures that any convergent point of the training process is a global minimum.
  arXiv  Detail & Related papers  (2025-03-12T17:33:13Z)
• A Functional Extension of Semi-Structured Networks [2.482050942288848]
  Semi-structured networks (SSNs) merge structures familiar from additive models with deep neural networks. Inspired by large-scale datasets, this paper explores extending SSNs to functional data. We propose a functional SSN method that retains the advantageous properties of classical functional regression approaches while also improving scalability.
  arXiv  Detail & Related papers  (2024-10-07T18:50:18Z)
• Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning [113.89327264634984]
  Few-shot class-incremental learning (FSCIL) confronts the challenge of integrating new classes into a model with minimal training samples. Traditional methods widely adopt static adaptation relying on a fixed parameter space to learn from data that arrive sequentially. We propose a dual selective SSM projector that dynamically adjusts the projection parameters based on the intermediate features for dynamic adaptation.
  arXiv  Detail & Related papers  (2024-07-08T17:09:39Z)
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
  We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs) Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators. Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
  arXiv  Detail & Related papers  (2024-05-22T17:23:15Z)
• Task adaption by biologically inspired stochastic comodulation [8.59194778459436]
  We show that fine-tuning convolutional networks by gain modulation improves on deterministic gain modulation. Our results suggest that comodulation representations can enhance learning efficiency and performance in multi-task learning.
  arXiv  Detail & Related papers  (2023-11-25T15:21:03Z)
• Accelerating Toeplitz Neural Network with Constant-time Inference Complexity [21.88774274472737]
  Toeplitz Neural Networks (TNNs) have exhibited outstanding performance in various sequence modeling tasks. They outperform commonly used Transformer-based models while benefiting from log-linear space-time complexities. In this paper, we aim to combine the strengths of TNNs and State Space Models (SSMs) by converting TNNs to SSMs during inference.
  arXiv  Detail & Related papers  (2023-11-15T07:50:57Z)
• Sparse Modular Activation for Efficient Sequence Modeling [94.11125833685583]
  Recent models combining Linear State Space Models with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. Current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. We introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely activate sub-modules for sequence elements in a differentiable manner.
  arXiv  Detail & Related papers  (2023-06-19T23:10:02Z)
• ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction [82.81767856234956]
  This paper proposes a new learning framework named ConCerNet to improve the trustworthiness of the DNN based dynamics modeling. We show that our method consistently outperforms the baseline neural networks in both coordinate error and conservation metrics.
  arXiv  Detail & Related papers  (2023-02-11T21:07:30Z)
• NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer [45.47667026025716]
  We propose a novel, robust and accelerated iteration that relies on two key elements. The convergence and stability of the obtained method, referred to as NAG-GS, are first studied extensively. We show that NAG-arity is competitive with state-the-art methods such as momentum SGD with weight decay and AdamW for the training of machine learning models.
  arXiv  Detail & Related papers  (2022-09-29T16:54:53Z)
• Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability [67.8426046908398]
  Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. This paper presents MetaPG, an evolutionary method for automated design of actor-critic loss functions.
  arXiv  Detail & Related papers  (2022-04-08T20:46:16Z)

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.