# Visual Encoding and Debiasing for CTR Prediction

arXiv: https://arxiv.org/abs/2205.04168 · HTML: https://mlsanity.com/paper/2205.04168/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2022.

## Built on by (most cited first, 5 of 5)

- [GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models](https://mlsanity.com/paper/2406.14550/) (2024)
- [Online Learning of Multiple Tasks and Their Relationships : Testing on Spam Email Data and EEG Signals Recorded in Construction Fields](https://mlsanity.com/paper/2406.18311/) (2024)
- [DashCLIP: Leveraging multimodal models for generating semantic embeddings for DoorDash](https://mlsanity.com/paper/2504.07110/) (2025)
- [Real-Time Summarization of Twitter](https://mlsanity.com/paper/2407.08125/) (2024)
- [PinDCO: Whole-Page Aware Dynamic Creative Optimization at Scale](https://mlsanity.com/paper/2609.11943/) (2026)

## Abstract (arXiv)

Extracting expressive visual features is crucial for accurate Click-Through-Rate (CTR) prediction in visual search advertising systems. Current commercial systems use off-the-shelf visual encoders to facilitate fast online service. However, the extracted visual features are coarse-grained and/or biased. In this paper, we present a visual encoding framework for CTR prediction to overcome these problems. The framework is based on contrastive learning which pulls positive pairs closer and pushes negative pairs apart in the visual feature space. To obtain fine-grained visual features,we present contrastive learning supervised by click through data to fine-tune the visual encoder. To reduce sample selection bias, firstly we train the visual encoder offline by leveraging both unbiased self-supervision and click supervision signals. Secondly, we incorporate a debiasing network in the online CTR predictor to adjust the visual features by contrasting high impression items with selected items with lower impressions.We deploy the framework in the visual sponsor search system at Alibaba. Offline experiments on billion-scale datasets and online experiments demonstrate that the proposed framework can make accurate and unbiased predictions.