# Attentive Pooling Networks

arXiv: https://arxiv.org/abs/1602.03609 · HTML: https://mlsanity.com/paper/1602.03609/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2016.

## Built on by (most cited first, 28 of 28)

- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training](https://mlsanity.com/paper/2310.02227/) (2023)
- [Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning](https://mlsanity.com/paper/2103.07552/) (2021)
- [Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length](https://mlsanity.com/paper/2411.03753/) (2024)
- [Contrastive Fine-tuning Improves Robustness for Neural Rankers](https://mlsanity.com/paper/2105.12932/) (2021)
- [CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals](https://mlsanity.com/paper/2106.05544/) (2021)
- [Leveraging Pretrained Representations with Task-related Keywords for Alzheimer's Disease Detection](https://mlsanity.com/paper/2303.08019/) (2023)
- [An Explainable CNN Approach for Medical Codes Prediction from Clinical Text](https://mlsanity.com/paper/2101.11430/) (2021)
- [Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge](https://mlsanity.com/paper/2104.05216/) (2021)
- [Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems](https://mlsanity.com/paper/2306.13307/) (2023)
- [SENSE models: an open source solution for multilingual and multimodal semantic-based tasks](https://mlsanity.com/paper/2509.12093/) (2025)
- [Learning to Select from Multiple Options](https://mlsanity.com/paper/2212.00301/) (2022)
- [Learning Intuitive Policies Using Action Features](https://mlsanity.com/paper/2201.12658/) (2022)
- [HieNet: Bidirectional Hierarchy Framework for Automated ICD Coding](https://mlsanity.com/paper/2212.04891/) (2022)
- [Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR](https://mlsanity.com/paper/2409.08797/) (2024)
- [Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation](https://mlsanity.com/paper/2606.22901/) (2026)
- [A Multi-Size Neural Network with Attention Mechanism for Answer Selection](https://mlsanity.com/paper/2105.03278/) (2021)
- [Data-driven Smart Ponzi Scheme Detection](https://mlsanity.com/paper/2108.09305/) (2021)
- [An Interpretable Framework for Drug-Target Interaction with Gated Cross Attention](https://mlsanity.com/paper/2109.08360/) (2021)
- [Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology](https://mlsanity.com/paper/2111.14283/) (2021)
- [A Hierarchical Regression Chain Framework for Affective Vocal Burst Recognition](https://mlsanity.com/paper/2303.08027/) (2023)
- [Hierarchical Ranking for Answer Selection](https://mlsanity.com/paper/2102.00677/) (2021)
- [Best-Answer Prediction in Q&A Sites Using User Information](https://mlsanity.com/paper/2212.08475/) (2022)
- [Structural Self-Supervised Objectives for Transformers](https://mlsanity.com/paper/2309.08272/) (2023)
- [Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context](https://mlsanity.com/paper/2401.12671/) (2024)
- [A Systematic Evaluation of Molecular Mixture Behavior Prediction](https://mlsanity.com/paper/2605.29698/) (2026)
- [TokenMapper: A Step Toward Interoperable Speech Token Translation](https://mlsanity.com/paper/2609.12563/) (2026)
- [Domain-Adaptive Dual-Gating Mixture of Experts for Generalizable Speech Deepfake Detection](https://mlsanity.com/paper/2609.33709/) (2026)

## Abstract (arXiv)

In this work, we propose Attentive Pooling (AP), a two-way attention mechanism for discriminative model training. In the context of pair-wise ranking or classification with neural networks, AP enables the pooling layer to be aware of the current input pair, in a way that information from the two input items can directly influence the computation of each other's representations. Along with such representations of the paired inputs, AP jointly learns a similarity measure over projected segments (e.g. trigrams) of the pair, and subsequently, derives the corresponding attention vector for each input to guide the pooling. Our two-way attention mechanism is a general framework independent of the underlying representation learning, and it has been applied to both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in our studies. The empirical results, from three very different benchmark tasks of question answering/answer selection, demonstrate that our proposed models outperform a variety of strong baselines and achieve state-of-the-art performance in all the benchmarks.