paper-with-me

Papers

FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression

2025-10-01 · Yifei Gao, Yong Chen, Chen Zhang arxiv

Functional data play a pivotal role across science and engineering, yet their infinite-dimensional nature makes representation learning challenging. Conventional statistical models depend on pre-chosen basis expansions or kernels, limiting the flexibility of data-driven discovery, while many deep-learning pipelines treat functions as fixed-grid vectors, ignoring inherent continuity. In this paper, we introduce Functional Attention with a Mixture-of-Experts (FAME), an end-to-end, fully data-driven framework for function-on-function regression. FAME forms continuous attention by coupling a bidirectional neural controlled differential equation with MoE-driven vector fields to capture intra-functional continuity, and further fuses change to inter-functional dependencies via multi-head cross attention. Extensive experiments on synthetic and real-world functional-regression benchmarks show that FAME achieves state-of-the-art accuracy, strong robustness to arbitrarily sampled discrete observations of functions.

📄 PDF Abstract BibTeX arXiv:2510.00621

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

BrainStack: Neuro-MoE with Functionally Guided Expert Routing for EEG-Based Language Decoding

2026-01-29 · Ziyi Zhao, Jinzhao Zhou, Xiaowei Jiang, Beining Cao 외 arxiv

Decoding linguistic information from electroencephalography (EEG) remains challenging due to the brain's distributed and nonlinear organization. We present BrainStack, a functionally guided neuro-mixture-of-experts (Neur…

Routing-Free Mixture-of-Experts

2026-04-01 · Yilun Liu, Jinru Han, Sikuan Yan, Volker Tresp 외 arxiv

Standard Mixture-of-Experts (MoE) models rely on centralized routing mechanisms that introduce rigid inductive biases. We propose Routing-Free MoE which eliminates any hard-coded centralized designs including external ro…

FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting

2026-06-08 · Qianyang Li, Xingjun Zhang, Shaoxun Wang, Tao Peng 외 arxiv

Large-scale retail and industrial forecasting systems contain many heterogeneous time series whose lifecycle, sparsity, volatility, seasonality, spectral patterns, and contextual sensitivity differ substantially. A singl…

Time Series Forecasting

Frequency-Adaptive Pan-Sharpening with Mixture of Experts

2024-01-04 · Xuanhua He, Keyu Yan, Rui Li, Chengjun Xie 외

Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance. Although the inborn connection wit…

Mixture-of-Experts

DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts

2024-12-13 · Tobias Braun, Mark Rothermel, Marcus Rohrbach, Anna Rohrbach

The proliferation of disinformation presents a growing threat to societal trust and democracy, necessitating robust and scalable Fact-Checking systems. In this work, we present Dynamic Evidence-based FAct-checking with M…

Claim VerificationFact Checking