Workshop on robustness of zero/few-shot learning in foundation models (R0-FoMo)

Ananth Balashankar · Saurabh Garg · Jindong Gu · Amrith Setlur · Yao Qin · Aditi Raghunathan · Ahmad Beirami

Ballroom A+B
[ Abstract ] Workshop Website
Fri 15 Dec, 6:50 a.m. PST

Recent advances in the capabilities of large foundation models have been catalyzed by repurposing pretrained models to domain specific use cases through few-shot learning methods like prompt-tuning, in-context-learning; and zero-shot learning based on task descriptions. Given a few labeled examples that outline a new task [T5, GPT2, T0, DALL-E, CLIP], these large foundation models have demonstrably improved upon previous few-shot learning benchmarks [T-few, LAION]. We are closer than ever to learn from very few examples; and recent works [Frozen, Flamingo] have proposed methods to use large language and vision transformer models directly on these few examples, instead of human annotation to create large datasets for fine-tuning. The lessons learned from past-work in counterfactual reasoning, domain adaptation, meta-learning, continual learning, and adversarial training have to be revisited with a new lens towards improving robustness of few-shot learning methods or learning from no supervision (i.e., unlabeled data) that scale to multiple tasks in a safe and responsible manner. In addition to leveraging few-shot learning methods with labeled examples, there is also significant potential in harnessing the power of unlabeled data. When labeled and unlabeled data are from the same distribution, semi-supervised learning methods can be modified to now utilize large foundation models that can further improve boost performance over purely few-shot algorithms. Furthermore, similar ideas need to be explored for unsupervised domain adaptation, to improve robustness of fine-tuned methods to distribution shifts when the unlabeled data distribution is much broader than the distribution from which the labeled examples are collected.

Live content is unavailable. Log in and register to view live content

Timezone: America/Los_Angeles »


Log in and register to view live content