paper-with-me

Papers

SWING: Unlocking Implicit Graph Representations for Graph Random Features

2026-02-13 · Alessandro Manenti, Avinava Dubey, Arijit Sehanobish, Cesare Alippi, Krzysztof Choromanski arxiv

We propose SWING: Space Walks for Implicit Network Graphs, a new class of algorithms for computations involving Graph Random Features on graphs given by implicit representations (i-graphs), where edge-weights are defined as bi-variate functions of feature vectors in the corresponding nodes. Those classes of graphs include several prominent examples, such as: $ε$-neighborhood graphs, used on regular basis in machine learning. Rather than conducting walks on graphs' nodes, those methods rely on walks in continuous spaces, in which those graphs are embedded. To accurately and efficiently approximate original combinatorial calculations, SWING applies customized Gumbel-softmax sampling mechanism with linearized kernels, obtained via random features coupled with importance sampling techniques. This algorithm is of its own interest. SWING relies on the deep connection between implicitly defined graphs and Fourier analysis, presented in this paper. SWING is accelerator-friendly and does not require input graph materialization. We provide detailed analysis of SWING and complement it with thorough experiments on different classes of i-graphs.

📄 PDF Abstract BibTeX arXiv:2602.12703

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

TTSWING: a Dataset for Table Tennis Swing Analysis

2023-06-30 · Che-Yu Chou, Zheng-Hao Chen, Yung-Hoh Sheu, Hung-Hsuan Chen 외

We introduce TTSWING, a novel dataset designed for table tennis swing analysis. This dataset comprises comprehensive swing information obtained through 9-axis sensors integrated into custom-made racket grips, accompanied…

ICLR: In-Context Learning of Representations

2024-12-29 · Core Francisco Park, Andrew Lee, Ekdeep Singh Lubana, Yongyi Yang 외

Recent work has demonstrated that semantics specified by pretraining data influence how representations of different concepts are organized in a large language model (LLM). However, given the open-ended nature of LLMs, e…

In-Context LearningLarge Language Model

SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation

2023-07-04 · Qi Yan, Zhengyang Liang, Yang song, Renjie Liao 외

Diffusion models based on permutation-equivariant networks can learn permutation-invariant distributions for graph data. However, in comparison to their non-invariant counterparts, we have found that these invariant mode…

DenoisingGraph Generation

Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes

2024-06-25 · Qi Ma, Danda Pani Paudel, Ender Konukoglu, Luc van Gool

Neural implicit functions have demonstrated significant importance in various areas such as computer vision, graphics. Their advantages include the ability to represent complex shapes and scenes with high fidelity, smoot…

GPUimage-classificationImage ClassificationNeRF+1

Linear socio-demographic representations emerge in Large Language Models from indirect cues

2025-12-10 · Paul Bouchaud, Pedro Ramaciotti arxiv

We investigate how LLMs encode sociodemographic attributes of human conversational partners inferred from indirect cues such as names and occupations. We show that LLMs develop linear representations of user demographics…