Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping

While Transformers have enabled tremendous progress in various application settings, such architectures still lag behind traditional symbolic planners for solving complex decision making tasks. In this work, we demonstrate how to train Transformers to solve complex planning tasks and present Searchformer, a Transformer model that optimally solves previously unseen Sokoban puzzles 93.7% of the time, while using up to 26.8% fewer search steps than standard $A^*$ search. Searchformer is an encoder-decoder Transformer model trained to predict the search dynamics of $A^*$. This model is then fine-tuned via expert iterations to perform fewer search steps than $A^*$ search while still generating an optimal plan. In our training method, $A^*$'s search dynamics are expressed as a token sequence outlining when task states are added and removed into the search tree during symbolic planning. In our ablation studies on maze navigation, we find that Searchformer significantly outperforms baselines that predict the optimal plan directly with a 5-10$\times$ smaller model size and a 10$\times$ smaller training dataset. We also demonstrate how Searchformer scales to larger and more complex decision making tasks like Sokoban with improved percentage of solved tasks and shortened search dynamics.

A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale

Shampoo is an online and stochastic optimization algorithm belonging to the AdaGrad family of methods for training neural networks. It constructs a block-diagonal preconditioner where each block consists of a coarse Kronecker product approximation to full-matrix AdaGrad for each parameter of the neural network. In this work, we provide a complete description of the algorithm as well as the performance optimizations that our implementation leverages to train deep networks at-scale in PyTorch. Our implementation enables fast multi-GPU distributed data-parallel training by distributing the memory and computation associated with blocks of each parameter via PyTorch's DTensor data structure and performing an AllGather primitive on the computed search directions at each iteration. This major performance enhancement enables us to achieve at most a 10% performance reduction in per-step wall-clock time compared against standard diagonal-scaling-based adaptive gradient methods. We validate our implementation by performing an ablation study on training ImageNet ResNet50, demonstrating Shampoo's superiority over standard training recipes with minimal hyperparameter tuning.

DINOv2: Learning Robust Visual Features without Supervision

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any system by producing all-purpose visual features, i.e., features that work across image distributions and tasks without finetuning. This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. We revisit existing approaches and combine different techniques to scale our pretraining in terms of data and model size. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature. In terms of models, we train a ViT model (Dosovitskiy et al., 2020) with 1B parameters and distill it into a series of smaller models that surpass the best available all-purpose features, OpenCLIP (Ilharco et al., 2021) on most of the benchmarks at image and pixel levels.

Green Federated Learning

The rapid progress of AI is fueled by increasingly large and computationally intensive machine learning models and datasets. As a consequence, the amount of compute used in training state-of-the-art models is exponentially increasing (doubling every 10 months between 2015 and 2022), resulting in a large carbon footprint. Federated Learning (FL) - a collaborative machine learning technique for training a centralized model using data of decentralized entities - can also be resource-intensive and have a significant carbon footprint, particularly when deployed at scale. Unlike centralized AI that can reliably tap into renewables at strategically placed data centers, cross-device FL may leverage as many as hundreds of millions of globally distributed end-user devices with diverse energy sources. Green AI is a novel and important research area where carbon footprint is regarded as an evaluation criterion for AI, alongside accuracy, convergence speed, and other metrics. In this paper, we propose the concept of Green FL, which involves optimizing FL parameters and making design choices to minimize carbon emissions consistent with competitive performance and training time. The contributions of this work are two-fold. First, we adopt a data-driven approach to quantify the carbon emissions of FL by directly measuring real-world at-scale FL tasks running on millions of phones. Second, we present challenges, guidelines, and lessons learned from studying the trade-off between energy efficiency, performance, and time-to-train in a production FL system. Our findings offer valuable insights into how FL can reduce its carbon footprint, and they provide a foundation for future research in the area of Green AI.

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. We introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative approach for self-supervised learning from images. The idea behind I-JEPA is simple: from a single context block, predict the representations of various target blocks in the same image. A core design choice to guide I-JEPA towards producing semantic representations is the masking strategy; specifically, it is crucial to (a) predict several target blocks in the image, (b) sample target blocks with sufficiently large scale (occupying 15%-20% of the image), and (c) use a sufficiently informative (spatially distributed) context block. Empirically, when combined with Vision Transformers, we find I-JEPA to be highly scalable. For instance, we train a ViT-Huge/16 on ImageNet using 32 A100 GPUs in under 38 hours to achieve strong downstream performance across a wide range of tasks requiring various levels of abstraction, from linear classification to object counting and depth prediction.

Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning

An oft-cited challenge of federated learning is the presence of heterogeneity. \emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \emph{System heterogeneity} refers to the fact that client devices have different system capabilities. A considerable number of federated optimization methods address this challenge. In the literature, empirical evaluations usually start federated training from random initialization. However, in many practical applications of federated learning, the server has access to proxy data for the training task that can be used to pre-train a model before starting federated training. We empirically study the impact of starting from a pre-trained model in federated learning using four standard federated learning benchmark datasets. Unsurprisingly, starting from a pre-trained model reduces the training time required to reach a target error rate and enables the training of more accurate models (up to 40\%) than is possible when starting from random initialization. Surprisingly, we also find that starting federated learning from a pre-trained initialization reduces the effect of both data and system heterogeneity. We recommend that future work proposing and evaluating federated optimization methods evaluate the performance when starting from random and pre-trained initializations. We also believe this study raises several questions for further work on understanding the role of heterogeneity in federated optimization.

The Hidden Uniform Cluster Prior in Self-Supervised Learning

A successful paradigm in representation learning is to perform self-supervised pretraining using tasks based on mini-batch statistics (e.g., SimCLR, VICReg, SwAV, MSN). We show that in the formulation of all these methods is an overlooked prior to learn features that enable uniform clustering of the data. While this prior has led to remarkably semantic representations when pretraining on class-balanced data, such as ImageNet, we demonstrate that it can hamper performance when pretraining on class-imbalanced data. By moving away from conventional uniformity priors and instead preferring power-law distributed feature clusters, we show that one can improve the quality of the learned representations on real-world class-imbalanced datasets. To demonstrate this, we develop an extension of the Masked Siamese Networks (MSN) method to support the use of arbitrary features priors.

Where to Begin? Exploring the Impact of Pre-Training and Initialization in Federated Learning

An oft-cited challenge of federated learning is the presence of data heterogeneity -- the data at different clients may follow very different distributions. Several federated optimization methods have been proposed to address these challenges. In the literature, empirical evaluations usually start federated training from a random initialization. However, in many practical applications of federated learning, the server has access to proxy data for the training task which can be used to pre-train a model before starting federated training. We empirically study the impact of starting from a pre-trained model in federated learning using four common federated learning benchmark datasets. Unsurprisingly, starting from a pre-trained model reduces the training time required to reach a target error rate and enables training more accurate models (by up to 40\%) than is possible than when starting from a random initialization. Surprisingly, we also find that the effect of data heterogeneity is much less significant when starting federated training from a pre-trained initialization. Rather, when starting from a pre-trained model, using an adaptive optimizer at the server, such as \textsc{FedAdam}, consistently leads to the best accuracy. We recommend that future work proposing and evaluating federated optimization methods consider the performance when starting both random and pre-trained initializations. We also believe this study raises several questions for further work on understanding the role of heterogeneity in federated optimization.

Positive Unlabeled Contrastive Learning

Self-supervised pretraining on unlabeled data followed by supervised finetuning on labeled data is a popular paradigm for learning from limited labeled examples. In this paper, we investigate and extend this paradigm to the classical positive unlabeled (PU) setting - the weakly supervised task of learning a binary classifier only using a few labeled positive examples and a set of unlabeled samples. We propose a novel PU learning objective positive unlabeled Noise Contrastive Estimation (puNCE) that leverages the available explicit (from labeled samples) and implicit (from unlabeled samples) supervision to learn useful representations from positive unlabeled input data. The underlying idea is to assign each training sample an individual weight; labeled positives are given unit weight; unlabeled samples are duplicated, one copy is labeled positive and the other as negative with weights $\pi$ and $(1-\pi)$ where $\pi$ denotes the class prior. Extensive experiments across vision and natural language tasks reveal that puNCE consistently improves over existing unsupervised and supervised contrastive baselines under limited supervision.

FedShuffle: Recipes for Better Use of Local Work in Federated Learning

The practice of applying several local updates before aggregation across clients has been empirically shown to be a successful approach to overcoming the communication bottleneck in Federated Learning (FL). In this work, we propose a general recipe, FedShuffle, that better utilizes the local updates in FL, especially in the heterogeneous regime. Unlike many prior works, FedShuffle does not assume any uniformity in the number of updates per device. Our FedShuffle recipe comprises four simple-yet-powerful ingredients: 1) local shuffling of the data, 2) adjustment of the local learning rates, 3) update weighting, and 4) momentum variance reduction (Cutkosky and Orabona, 2019). We present a comprehensive theoretical analysis of FedShuffle and show that both theoretically and empirically, our approach does not suffer from the objective function mismatch that is present in FL methods which assume homogeneous updates in heterogeneous FL setups, e.g., FedAvg (McMahan et al., 2017). In addition, by combining the ingredients above, FedShuffle improves upon FedNova (Wang et al., 2020), which was previously proposed to solve this mismatch. We also show that FedShuffle with momentum variance reduction can improve upon non-local methods under a Hessian similarity assumption. Finally, through experiments on synthetic and real-world datasets, we illustrate how each of the four ingredients used in FedShuffle helps improve the use of local updates in FL.