LSEBMCL replays EBM-generated pseudo-samples from previous tasks to reduce catastrophic forgetting, reporting top average scores on several NLP continual learning benchmarks.
Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this work, we explore joint energy-based model (EBM) training during the finetuning of pretrained text encoders (e.g., Roberta) for natural language understanding (NLU) tasks. Our experiments show that EBM training can help the model reach a better calibration that is competitive to strong baselines, with little or no loss in accuracy. We discuss three variants of energy functions (namely scalar, hidden, and sharp-hidden) that can be defined on top of a text encoder, and compare them in experiments. Due to the discreteness of text data, we adopt noise contrastive estimation (NCE) to train the energy-based model. To make NCE training more effective, we train an auto-regressive noise model with the masked language model (MLM) objective.
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
LSEBMCL: A Latent Space Energy-Based Model for Continual Learning
LSEBMCL replays EBM-generated pseudo-samples from previous tasks to reduce catastrophic forgetting, reporting top average scores on several NLP continual learning benchmarks.