What Variables Affect Out-Of-Distribution Generalization in Pretrained Models?

Embeddings produced by pre-trained deep neural networks (DNNs) are widely used; however, their efficacy for downstream tasks can vary widely. We study the factors influencing out-of-distribution (OOD) generalization of pre-trained DNN embeddings through the lens of the tunnel effect hypothesis, which suggests deeper DNN layers compress representations and hinder OOD performance. Contrary to earlier work, we find the tunnel effect is not universal. Based on 10,584 linear probes, we study the conditions that mitigate the tunnel effect by varying DNN architecture, training dataset, image resolution, and augmentations. We quantify each variable's impact using a novel SHAP analysis. Our results emphasize the danger of generalizing findings from toy datasets to broader contexts.

PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology

Foundation models in computational pathology promise to unlock the development of new clinical decision support systems and models for precision medicine. However, there is a mismatch between most clinical analysis, which is defined at the level of one or more whole slide images, and foundation models to date, which process the thousands of image tiles contained in a whole slide image separately. The requirement to train a network to aggregate information across a large number of tiles in multiple whole slide images limits these models' impact. In this work, we present a slide-level foundation model for H&E-stained histopathology, PRISM, that builds on Virchow tile embeddings and leverages clinical report text for pre-training. Using the tile embeddings, PRISM produces slide-level embeddings with the ability to generate clinical reports, resulting in several modes of use. Using text prompts, PRISM achieves zero-shot cancer detection and sub-typing performance approaching and surpassing that of a supervised aggregator model. Using the slide embeddings with linear classifiers, PRISM surpasses supervised aggregator models. Furthermore, we demonstrate that fine-tuning of the PRISM slide encoder yields label-efficient training for biomarker prediction, a task that typically suffers from low availability of training data; an aggregator initialized with PRISM and trained on as little as 10% of the training data can outperform a supervised baseline that uses all of the data.

DMC4ML: Data Movement Complexity for Machine Learning

The greatest demand for today's computing is machine learning. This paper analyzes three machine learning algorithms: transformers, spatial convolution, and FFT. The analysis is novel in three aspects. First, it measures the cost of memory access on an abstract memory hierarchy, instead of traditional time or space complexity. Second, the analysis is asymptotic and identifies the primary sources of the memory cost. Finally, the result is symbolic, which can be used to select algorithmic parameters such as the group size in grouped query attention for any dimension size and number of heads and the batch size for batched convolution for any image size and kernel size.

BloomVQA: Assessing Hierarchical Multi-modal Comprehension

We propose a novel VQA dataset, based on picture stories designed for educating young children, that aims to facilitate comprehensive evaluation and characterization of vision-language models on comprehension tasks. Unlike current VQA datasets that often focus on fact-based memorization and simple reasoning tasks without principled scientific grounding, we collect data containing tasks reflecting different levels of comprehension and underlying cognitive processes, as laid out in Bloom's Taxonomy, a classic framework widely adopted in education research. The proposed BloomVQA dataset can be mapped to a hierarchical graph-based representation of visual stories, enabling automatic data augmentation and novel measures characterizing model consistency across the underlying taxonomy. We demonstrate graded evaluation and reliability analysis based on our proposed consistency metrics on state-of-the-art vision-language models. Our results suggest that, while current models achieve the most gain on low-level comprehension tasks, they generally fall short on high-level tasks requiring more advanced comprehension and cognitive skills, as 38.0% drop in VQA accuracy is observed comparing lowest and highest level tasks. Furthermore, current models show consistency patterns misaligned with human comprehension in various scenarios, suggesting emergent structures of model behaviors.

Continual Learning: Applications and the Road Forward

Continual learning is a sub-field of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past. In this work, we take a step back, and ask: "Why should one care about continual learning in the first place?". We set the stage by surveying recent continual learning papers published at three major machine learning conferences, and show that memory-constrained settings dominate the field. Then, we discuss five open problems in machine learning, and even though they seem unrelated to continual learning at first sight, we show that continual learning will inevitably be part of their solution. These problems are model-editing, personalization, on-device learning, faster (re-)training and reinforcement learning. Finally, by comparing the desiderata from these unsolved problems and the current assumptions in continual learning, we highlight and discuss four future directions for continual learning research. We hope that this work offers an interesting perspective on the future of continual learning, while displaying its potential value and the paths we have to pursue in order to make it successful. This work is the result of the many discussions the authors had at the Dagstuhl seminar on Deep Continual Learning, in March 2023.

Virchow: A Million-Slide Digital Pathology Foundation Model

Computational pathology uses artificial intelligence to enable precision medicine and decision support systems through the analysis of whole slide images. It has the potential to revolutionize the diagnosis and treatment of cancer. However, a major challenge to this objective is that for many specific computational pathology tasks the amount of data is inadequate for development. To address this challenge, we created Virchow, a 632 million parameter deep neural network foundation model for computational pathology. Using self-supervised learning, Virchow is trained on 1.5 million hematoxylin and eosin stained whole slide images from diverse tissue groups, which is orders of magnitude more data than previous works. When evaluated on downstream tasks including tile-level pan-cancer detection and subtyping and slide-level biomarker prediction, Virchow outperforms state-of-the-art systems both on internal datasets drawn from the same population as the pretraining data as well as external public datasets. Virchow achieves 93% balanced accuracy for pancancer tile classification, and AUCs of 0.983 for colon microsatellite instability status prediction and 0.967 for breast CDH1 status prediction. The gains in performance highlight the importance of pretraining on massive pathology image datasets, suggesting pretraining on even larger datasets could continue improving performance for many high-impact applications where limited amounts of training data are available, such as drug outcome prediction.

GRASP: A Rehearsal Policy for Efficient Online Continual Learning

Continual learning (CL) in deep neural networks (DNNs) involves incrementally accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is that non-stationary data streams cause catastrophic forgetting of previously learned abilities. Rehearsal is a popular and effective way to mitigate this problem, which is storing past observations in a buffer and mixing them with new observations during learning. This leads to a question: Which stored samples should be selected for rehearsal? Choosing samples that are best for learning, rather than simply selecting them at random, could lead to significantly faster learning. For class incremental learning, prior work has shown that a simple class balanced random selection policy outperforms more sophisticated methods. Here, we revisit this question by exploring a new sample selection policy called GRASP. GRASP selects the most prototypical (class representative) samples first and then gradually selects less prototypical (harder) examples to update the DNN. GRASP has little additional compute or memory overhead compared to uniform selection, enabling it to scale to large datasets. We evaluate GRASP and other policies by conducting CL experiments on the large-scale ImageNet-1K and Places-LT image classification datasets. GRASP outperforms all other rehearsal policies. Beyond vision, we also demonstrate that GRASP is effective for CL on five text classification datasets.

Understanding the Benefits of Image Augmentations

Image Augmentations are widely used to reduce overfitting in neural networks. However, the explainability of their benefits largely remains a mystery. We study which layers of residual neural networks (ResNets) are most affected by augmentations using Centered Kernel Alignment (CKA). We do so by analyzing models of varying widths and depths, as well as whether their weights are initialized randomly or through transfer learning. We find that the pattern of how the layers are affected depends on the model's depth, and that networks trained with augmentation that use information from two images affect the learned weights significantly more than augmentations that operate on a single image. Deeper layers of ResNets initialized with ImageNet-1K weights and fine-tuned receive more impact from the augmentations than early layers. Understanding the effects of image augmentations on CNNs will have a variety of applications, such as determining how far back one needs to fine-tune a network and which layers should be frozen when implementing layer freezing algorithms.

Overcoming the Stability Gap in Continual Learning

In many real-world applications, deep neural networks are retrained from scratch as a dataset grows in size. Given the computational expense for retraining networks, it has been argued that continual learning could make updating networks more efficient. An obstacle to achieving this goal is the stability gap, which refers to an observation that when updating on new data, performance on previously learned data degrades before recovering. Addressing this problem would enable continual learning to learn new data with fewer network updates, resulting in increased computational efficiency. We study how to mitigate the stability gap in rehearsal (or experience replay), a widely employed continual learning method. We test a variety of hypotheses to understand why the stability gap occurs. This leads us to discover a method that vastly reduces this gap. In experiments on a large-scale incremental class learning setting, we are able to significantly reduce the number of network updates to recover performance. Our work has the potential to advance the state-of-the-art in continual learning for real-world applications along with reducing the carbon footprint required to maintain updated neural networks.

How Efficient Are Today's Continual Learning Algorithms?

Supervised Continual learning involves updating a deep neural network (DNN) from an ever-growing stream of labeled data. While most work has focused on overcoming catastrophic forgetting, one of the major motivations behind continual learning is being able to efficiently update a network with new information, rather than retraining from scratch on the training dataset as it grows over time. Despite recent continual learning methods largely solving the catastrophic forgetting problem, there has been little attention paid to the efficiency of these algorithms. Here, we study recent methods for incremental class learning and illustrate that many are highly inefficient in terms of compute, memory, and storage. Some methods even require more compute than training from scratch! We argue that for continual learning to have real-world applicability, the research community cannot ignore the resources used by these algorithms. There is more to continual learning than mitigating catastrophic forgetting.