Imagen de Portada

Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ennadir, Sofiane, Zólyomi, Levente, Smirnov, Oleg, Wang, Tianze, Pertoft, John, Cornell, Filip, Cao, Lele
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospects
por: Zólyomi, Levente, et al.
Publicado: (2025)

Enhancing Graph Classification Robustness with Singular Pooling
por: Ennadir, Sofiane, et al.
Publicado: (2025)

Be Wary of Your Time Series Preprocessing
por: Ennadir, Sofiane, et al.
Publicado: (2026)

Expressivity of Representation Learning on Continuous-Time Dynamic Graphs: An Information-Flow Centric Review
por: Ennadir, Sofiane, et al.
Publicado: (2024)

Frequency Matters: When Time Series Foundation Models Fail Under Spectral Shift
por: Wang, Tianze, et al.
Publicado: (2025)

Joint Embeddings Go Temporal
por: Ennadir, Sofiane, et al.
Publicado: (2025)

Interpretable Graph Neural Networks for Tabular Data
por: Alkhatib, Amr, et al.
Publicado: (2023)

Are We Really Measuring Progress? Transferring Insights from Evaluating Recommender Systems to Temporal Link Prediction
por: Cornell, Filip, et al.
Publicado: (2025)

On the Power of Heuristics in Temporal Graphs
por: Cornell, Filip, et al.
Publicado: (2025)

UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
por: Huang, Minbin, et al.
Publicado: (2026)

Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs
por: Su, Zhixiang, et al.
Publicado: (2025)

Understanding Pooling in Graph Neural Networks
por: Grattarola, Daniele, et al.
Publicado: (2021)

SSHPool: The Separated Subgraph-based Hierarchical Pooling
por: Xu, Zhuo, et al.
Publicado: (2024)

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
por: Abbahaddou, Yassine, et al.
Publicado: (2024)

Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification
por: Mamtani, Sumit, et al.
Publicado: (2025)

On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processing
por: Dong, Zeming, et al.
Publicado: (2022)

Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning
por: Trumpp, Raphael, et al.
Publicado: (2025)

On the (Non) Injectivity of Piecewise Linear Janossy Pooling
por: Reshef, Ilai, et al.
Publicado: (2025)

A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizability
por: Wang, Pengyun, et al.
Publicado: (2024)

ASDFormer: A Transformer with Mixtures of Pooling-Classifier Experts for Robust Autism Diagnosis and Biomarker Discovery
por: Izadi, Mohammad, et al.
Publicado: (2025)

STAMP: Spatial-Temporal Adapter with Multi-Head Pooling
por: Shook, Brad, et al.
Publicado: (2025)

LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisation
por: Noravesh, Farshad, et al.
Publicado: (2025)

Enhance Hyperbolic Representation Learning via Second-order Pooling
por: Song, Kun, et al.
Publicado: (2024)

Beyond Pooling: Matching for Robust Generalization under Data Heterogeneity
por: Roy, Ayush, et al.
Publicado: (2026)

Subgraph Pooling: Tackling Negative Transfer on Graphs
por: Wang, Zehong, et al.
Publicado: (2024)

ENADPool: The Edge-Node Attention-based Differentiable Pooling for Graph Neural Networks
por: Zhao, Zhehan, et al.
Publicado: (2024)

Mutual Information as Intrinsic Reward of Reinforcement Learning Agents for On-demand Ride Pooling
por: Zhang, Xianjie, et al.
Publicado: (2023)

Stochastic Subsampling With Average Pooling
por: Kim, Bum Jun, et al.
Publicado: (2024)

Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings
por: Seong, Jihyeon, et al.
Publicado: (2024)

player2vec: A Language Modeling Approach to Understand Player Behavior in Games
por: Wang, Tianze, et al.
Publicado: (2024)

SPGNN: Recognizing Salient Subgraph Patterns via Enhanced Graph Convolution and Pooling
por: Dong, Zehao, et al.
Publicado: (2024)

Contrastive Graph Pooling for Explainable Classification of Brain Networks
por: Xu, Jiaxing, et al.
Publicado: (2023)

Are We Wasting Time? A Fast, Accurate Performance Evaluation Framework for Knowledge Graph Link Predictors
por: Cornell, Filip, et al.
Publicado: (2024)

UniPrompt-CL: Sustainable Continual Learning in Medical AI with Unified Prompt Pools
por: Oh, Gyutae, et al.
Publicado: (2025)

Timing the Match: A Deep Reinforcement Learning Approach for Ride-Hailing and Ride-Pooling Services
por: Bao, Yiman, et al.
Publicado: (2025)

Enhancing Hyperspace Analogue to Language (HAL) Representations via Attention-Based Pooling for Text Classification
por: Sakour, Ali, et al.
Publicado: (2026)

Why Pool When You Can Flow? Active Learning with GFlowNets
por: Zhang, Renfei, et al.
Publicado: (2025)

PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for Cyber Defense
por: Cadet, Xavier, et al.
Publicado: (2025)

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
por: Nguyen, Quang Duc, et al.
Publicado: (2026)

Prompt Tuning Decision Transformers with Structured and Scalable Bandits
por: Rietz, Finn, et al.
Publicado: (2025)