Class-incremental learning requires models to continually acquire knowledge of new classes without forgetting old ones. Although pre-trained models have demonstrated strong performance in class-incremental learning, they remain susceptible to catastrophic forgetting when learning new concepts. Excessive plasticity in the models breaks generalizability and causes forgetting, while strong stability results in insufficient adaptation to new classes. This necessitates effective adaptation with minimal modifications to preserve the general knowledge of pre-trained models. To address this challenge, we first introduce a new parameter-efficient fine-tuning module 'Learn and Calibrate', or LuCA, designed to acquire knowledge through an adapter-calibrator couple, enabling effective adaptation with well-refined feature representations. Second, for each learning session, we deploy a sparse LuCA module on top of the last token just before the classifier, which we refer to as 'Token-level Sparse Calibration and Adaptation', or TOSCA. This strategic design improves the orthogonality between the modules and significantly reduces both training and inference complexity. By leaving the generalization capabilities of the pre-trained models intact and adapting exclusively via the last token, our approach achieves a harmonious balance between stability and plasticity. Extensive experiments demonstrate TOSCA's state-of-the-art performance while introducing ~8 times fewer parameters compared to prior methods.

The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability. Its development employed an open process that included participants from multiple fields. The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories, including violent crimes, nonviolent crimes, sex-related crimes, child sexual exploitation, indiscriminate weapons, suicide and self-harm, intellectual property, privacy, defamation, hate, sexual content, and specialized advice (election, financial, health, legal). Our method incorporates a complete assessment standard, extensive prompt datasets, a novel evaluation framework, a grading and reporting system, and the technical as well as organizational infrastructure for long-term support and evolution. In particular, the benchmark employs an understandable five-tier grading scale (Poor to Excellent) and incorporates an innovative entropy-based system-response evaluation. In addition to unveiling the benchmark, this report also identifies limitations of our method and of building safety benchmarks generally, including evaluator uncertainty and the constraints of single-turn interactions. This work represents a crucial step toward establishing global standards for AI risk and reliability evaluation while acknowledging the need for continued development in areas such as multiturn interactions, multimodal understanding, coverage of additional languages, and emerging hazard categories. Our findings provide valuable insights for model developers, system integrators, and policymakers working to promote safer AI deployment.

Fine-tuning models that have been pre-trained on large datasets has become a cornerstone of modern machine learning workflows. With the widespread availability of online model repositories, such as Hugging Face, it is now easier than ever to fine-tune pre-trained models for specific tasks. This raises a critical question: which pre-trained model is most suitable for a given task? This problem is called transferability estimation. In this work, we introduce two novel and effective metrics for estimating the transferability of pre-trained models. Our approach is grounded in viewing transferability as a measure of how easily a pre-trained model's representations can be trained to separate target classes, providing a unique perspective on transferability estimation. We rigorously evaluate the proposed metrics against state-of-the-art alternatives across diverse problem settings, demonstrating their robustness and practical utility. Additionally, we present theoretical insights that explain our metrics' efficacy and adaptability to various scenarios. We experimentally show that our metrics increase Kendall's Tau by up to 32% compared to the state-of-the-art baselines.

Continual Learning (CL) methods usually learn from all the available data. However, this is not the case in human cognition which efficiently focuses on key experiences while disregarding the redundant information. Similarly, not all data points in a dataset have equal potential; some can be more informative than others. This disparity may significantly impact the performance, as both the quality and quantity of samples directly influence the model's generalizability and efficiency. Drawing inspiration from this, we explore the potential of learning from important samples and present an empirical study for evaluating coreset selection techniques in the context of CL to stimulate research in this unexplored area. We train different continual learners on increasing amounts of selected samples and investigate the learning-forgetting dynamics by shedding light on the underlying mechanisms driving their improved stability-plasticity balance. We present several significant observations: learning from selectively chosen samples (i) enhances incremental accuracy, (ii) improves knowledge retention of previous tasks, and (iii) refines learned representations. This analysis contributes to a deeper understanding of selective learning strategies in CL scenarios.

We propose an AutoML system that enables model selection on clustering problems by leveraging optimal transport-based dataset similarity. Our objective is to establish a comprehensive AutoML pipeline for clustering problems and provide recommendations for selecting the most suitable algorithms, thus opening up a new area of AutoML beyond the traditional supervised learning settings. We compare our results against multiple clustering baselines and find that it outperforms all of them, hence demonstrating the utility of similarity-based automated model selection for solving clustering applications.

Data is a critical resource for Machine Learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that simplifies how data is used by ML tools and frameworks. Croissant makes datasets more discoverable, portable and interoperable, thereby addressing significant challenges in ML data management and responsible AI. Croissant is already supported by several popular dataset repositories, spanning hundreds of thousands of datasets, ready to be loaded into the most popular ML frameworks.

Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that leverages the generalization abilities of in-context learning observed in transformer architectures. Our method reframes meta-learning as a sequence modeling problem, enabling the transformer encoder to learn task context from support images and utilize it to predict query images. At the core of our approach lies the creation of diverse tasks generated using a combination of data augmentations and a mixing strategy that challenges the model during training while fostering generalization to unseen tasks at test time. Experimental results on benchmark datasets, including miniImageNet, CIFAR-fs, CUB, and Aircraft, showcase the superiority of our approach over existing unsupervised meta-learning baselines, establishing it as the new state-of-the-art in the field. Remarkably, our method achieves competitive results with supervised and self-supervised approaches, underscoring the efficacy of the model in leveraging generalization over memorization.

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models. We introduce a principled approach to specifying and constructing the benchmark, which for v0.5 covers only a single use case (an adult chatting to a general-purpose assistant in English), and a limited set of personas (i.e., typical users, malicious users, and vulnerable users). We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0.5 benchmark. We plan to release version 1.0 of the AI Safety Benchmark by the end of 2024. The v1.0 benchmark will provide meaningful insights into the safety of AI systems. However, the v0.5 benchmark should not be used to assess the safety of AI systems. We have sought to fully document the limitations, flaws, and challenges of v0.5. This release of v0.5 of the AI Safety Benchmark includes (1) a principled approach to specifying and constructing the benchmark, which comprises use cases, types of systems under test (SUTs), language and context, personas, tests, and test items; (2) a taxonomy of 13 hazard categories with definitions and subcategories; (3) tests for seven of the hazard categories, each comprising a unique set of test items, i.e., prompts. There are 43,090 test items in total, which we created with templates; (4) a grading system for AI systems against the benchmark; (5) an openly available platform, and downloadable tool, called ModelBench that can be used to evaluate the safety of AI systems on the benchmark; (6) an example evaluation report which benchmarks the performance of over a dozen openly available chat-tuned language models; (7) a test specification for the benchmark.

Class incremental learning (CIL) in an online continual learning setting strives to acquire knowledge on a series of novel classes from a data stream, using each data point only once for training. This is more realistic compared to offline modes, where it is assumed that all data from novel class(es) is readily available. Current online CIL approaches store a subset of the previous data which creates heavy overhead costs in terms of both memory and computation, as well as privacy issues. In this paper, we propose a new online CIL approach called FOCIL. It fine-tunes the main architecture continually by training a randomly pruned sparse subnetwork for each task. Then, it freezes the trained connections to prevent forgetting. FOCIL also determines the sparsity level and learning rate per task adaptively and ensures (almost) zero forgetting across all tasks without storing any replay data. Experimental results on 10-Task CIFAR100, 20-Task CIFAR100, and 100-Task TinyImagenet, demonstrate that our method outperforms the SOTA by a large margin. The code is publicly available at https://github.com/muratonuryildirim/FOCIL.

In few-shot learning, such as meta-learning, few-shot fine-tuning or in-context learning, the limited number of samples used to train a model have a significant impact on the overall success. Although a large number of sample selection strategies exist, their impact on the performance of few-shot learning is not extensively known, as most of them have been so far evaluated in typical supervised settings only. In this paper, we thoroughly investigate the impact of 20 sample selection strategies on the performance of 5 few-shot learning approaches over 8 image and 6 text datasets. In addition, we propose a new method for automatic combination of sample selection strategies (ACSESS) that leverages the strengths and complementary information of the individual strategies. The experimental results show that our method consistently outperforms the individual selection strategies, as well as the recently proposed method for selecting support examples for in-context learning. We also show a strong modality, dataset and approach dependence for the majority of strategies as well as their dependence on the number of shots - demonstrating that the sample selection strategies play a significant role for lower number of shots, but regresses to random selection at higher number of shots.