Ximei Wang

12

Papers

53

Total Citations

Papers (12)

STEM: Unleashing the Power of Embeddings for Multi-Task Recommendation

Long-Sequence Recommendation Models Need Decoupled Embeddings

Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning

From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models

Minimum Class Confusion for Versatile Domain Adaptation

On the Embedding Collapse when Scaling up Recommendation Models

Regressive Domain Adaptation for Unsupervised Keypoint Detection

Transferable Normalization: Towards Improving Transferability of Deep Neural Networks

Transferable Calibration with Lower Bias and Variance in Domain Adaptation

Debiased Self-Training for Semi-Supervised Learning

ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning

Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation