EffiMiniVLM: A Compact Dual-Encoder Regression Framework
This addresses the need for efficient multimodal models in e-commerce cold-start scenarios, though it appears incremental as it builds on existing encoder architectures with optimizations.
The paper tackles the problem of predicting product quality from multimodal information in cold-start scenarios by proposing EffiMiniVLM, a compact dual-encoder vision-language regression framework that achieves a CES score of 0.40 with only 27.7M parameters and 6.8 GFLOPs, making it 4x to 8x more resource-efficient than comparable methods.
Predicting product quality from multimodal item information is critical in cold-start scenarios, where user interaction history is unavailable and predictions must rely on images and textual metadata. However, existing vision-language models typically depend on large architectures and/or extensive external datasets, resulting in high computational cost. To address this, we propose EffiMiniVLM, a compact dual-encoder vision-language regression framework that integrates an EfficientNet-B0 image encoder and a MiniLM-based text encoder with a lightweight regression head. To improve training sample efficiency, we introduce a weighted Huber loss that leverages rating counts to emphasize more reliable samples, yielding consistent performance gains. Trained using only 20% of the Amazon Reviews 2023 dataset, the proposed model contains 27.7M parameters and requires 6.8 GFLOPs, yet achieves a CES score of 0.40 with the lowest resource cost in the benchmark. Despite its small size, it remains competitive with significantly larger models, achieving comparable performance while being approximately 4x to 8x more resource-efficient than other top-5 methods and being the only approach that does not use external datasets. Further analysis shows that scaling the data to 40% alone allows our model to overtake other methods, which use larger models and datasets, highlighting strong scalability despite the model's compact design.