GSASRec (Sequential)

Description

The GSASRec (Generalized Self-Attentive Sequential Recommendation) policy is an enhancement of SASRec designed to mitigate potential overconfidence issues that can arise from negative sampling during training. It incorporates modifications, often to the loss function or sampling strategy, to improve prediction calibration while retaining the core self-attention mechanism of SASRec for modeling sequences.

Policy Type: gsasrec Supports: embedding_policy, scoring_policy

Configuration Example

scoring_policy_gsasrec.yaml

policy_configs:
  scoring_policy: # Can also be used under embedding_policy
    policy_type: gsasrec
    # Training Hyperparameters
    batch_size: 32             # Samples per training batch
    n_epochs: 1                # Number of training epochs
    learning_rate: 0.001       # Optimizer learning rate
    dropout_rate: 0.5          # General dropout rate
    neg_per_positive: 1
    # Architecture Hyperparameters
    num_heads: 1               # Number of self-attention heads
    sequence_length: 200       # Maximum input sequence length
    embedding_dim: 128         # Dimensionality of embeddings/hidden layers

Reference

• Li, J., et al. (2021). gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling. CIKM. (Check citation details - arXiv date is late for CIKM 2021).