Search Results for author:
Found 4 papers, 0 papers with code
RINAS: Training with Dataset Shuffling Can Be General and Fast
However, loading shuffled data for large datasets incurs significant overhead in the deep learning pipeline and severely impacts the end-to-end training throughput.
Adaptive Gating in Mixture-of-Experts based Language Models
Existing MoE model adopts a fixed gating network where each token is computed by the same number of experts.
Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation
We employ a causal graph illuminating that duration is a confounding factor that concurrently affects video exposure and watch-time prediction -- the first effect on video causes the bias issue and should be eliminated, while the second effect on watch time originates from video intrinsic characteristics and should be preserved.
PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
In this setting with multiple and constrained goals, this paper discovers that a probabilistic strategic parameter regime can achieve better value compared to the standard regime of finding a single deterministic parameter.
