COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Learning

Retrieval augmentation, the practice of retrieving additional data from large auxiliary pools, has emerged as an effective technique for enhancing model performance in the low-data regime, e.g. few-shot learning. Prior approaches have employed only nearest-neighbor based strategies for data selection, which retrieve auxiliary samples with high similarity to instances in the target task. However, these approaches are prone to selecting highly redundant samples, since they fail to incorporate any notion of diversity. In our work, we first demonstrate that data selection strategies used in prior retrieval-augmented few-shot learning settings can be generalized using a class of functions known as Combinatorial Mutual Information (CMI) measures. We then propose COBRA (COmBinatorial Retrieval Augmentation), which employs an alternative CMI measure that considers both diversity and similarity to a target dataset. COBRA consistently outperforms previous retrieval approaches across image classification tasks and few-shot learning techniques when used to retrieve samples from LAION-2B. COBRA introduces negligible computational overhead to the cost of retrieval while providing significant gains in downstream model performance.

PRIMUS: Pretraining IMU Encoders with Multimodal Self-Supervision

Sensing human motions through Inertial Measurement Units (IMUs) embedded in personal devices has enabled significant applications in health and wellness. While labeled IMU data is scarce, we can collect unlabeled or weakly labeled IMU data to model human motions. For video or text modalities, the "pretrain and adapt" approach utilizes large volumes of unlabeled or weakly labeled data for pretraining, building a strong feature extractor, followed by adaptation to specific tasks using limited labeled data. This approach has not been widely adopted in the IMU domain for two reasons: (1) pretraining methods are poorly understood in the context of IMU, and (2) open-source pretrained models that generalize across datasets are rarely publicly available. In this paper, we aim to address the first issue by proposing PRIMUS, a method for PRetraining IMU encoderS. We conduct a systematic and unified evaluation of various self-supervised and multimodal learning pretraining objectives. Our findings indicate that using PRIMUS, which combines self-supervision, multimodal supervision, and nearest-neighbor supervision, can significantly enhance downstream performance. With fewer than 500 labeled samples per class, PRIMUS effectively enhances downstream performance by up to 15% in held-out test data, compared to the state-of-the-art multimodal training method. To benefit the broader community, our code and pre-trained IMU encoders will be made publicly available at github.com/nokia-bell-labs upon publication.

An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models

Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to produce high quality responses for instructions are becoming prohibitively expensive, especially as the number of tasks spanned by instruction datasets continues to increase. Active learning is effective in identifying useful subsets of samples to annotate from an unlabeled pool, but its high computational cost remains a barrier to its widespread applicability in the context of LLMs. To mitigate the annotation cost of SFT and circumvent the computational bottlenecks of active learning, we propose using experimental design. Experimental design techniques select the most informative samples to label, and typically maximize some notion of uncertainty and/or diversity. In our work, we implement a framework that evaluates several existing and novel experimental design techniques and find that these methods consistently yield significant gains in label efficiency with little computational overhead. On generative tasks, our methods achieve the same generalization performance with only $50\%$ of annotation cost required by random sampling.