Deep neural networks excel in supervised learning tasks but are constrained by the need for extensive labeled data. Self-supervised learning emerges as a promising alternative, allowing models to learn without explicit labels. Information theory, and notably the information bottleneck principle, has been pivotal in shaping deep neural networks. This principle focuses on optimizing the trade-off between compression and preserving relevant information, providing a foundation for efficient network design in supervised contexts. However, its precise role and adaptation in self-supervised learning remain unclear. In this work, we scrutinize various self-supervised learning approaches from an information-theoretic perspective, introducing a unified framework that encapsulates the \textit{self-supervised information-theoretic learning problem}. We weave together existing research into a cohesive narrative, delve into contemporary self-supervised methodologies, and spotlight potential research avenues and inherent challenges. Additionally, we discuss the empirical evaluation of information-theoretic quantities and their estimation methods. Overall, this paper furnishes an exhaustive review of the intersection of information theory, self-supervised learning, and deep neural networks.

Federated learning (FL) is a decentralized machine learning technique that enables multiple clients to collaboratively train models without requiring clients to reveal their raw data to each other. Although traditional FL trains a single global model with average performance among clients, statistical data heterogeneity across clients has resulted in the development of personalized FL (PFL), which trains personalized models with good performance on each client's data. A key challenge with PFL is how to facilitate clients with similar data to collaborate more in a situation where each client has data from complex distribution and cannot determine one another's distribution. In this paper, we propose a new PFL method (pFedMB) using multi-branch architecture, which achieves personalization by splitting each layer of a neural network into multiple branches and assigning client-specific weights to each branch. We also design an aggregation method to improve the communication efficiency and the model performance, with which each branch is globally updated with weighted averaging by client-specific weights assigned to the branch. pFedMB is simple but effective in facilitating each client to share knowledge with similar clients by adjusting the weights assigned to each branch. We experimentally show that pFedMB performs better than the state-of-the-art PFL methods using the CIFAR10 and CIFAR100 datasets.

This paper studies separating invariants: mappings on $D$ dimensional domains which are invariant to an appropriate group action, and which separate orbits. The motivation for this study comes from the usefulness of separating invariants in proving universality of equivariant neural network architectures. We observe that in several cases the cardinality of separating invariants proposed in the machine learning literature is much larger than the dimension $D$. As a result, the theoretical universal constructions based on these separating invariants is unrealistically large. Our goal in this paper is to resolve this issue. We show that when a continuous family of semi-algebraic separating invariants is available, separation can be obtained by randomly selecting $2D+1 $ of these invariants. We apply this methodology to obtain an efficient scheme for computing separating invariants for several classical group actions which have been studied in the invariant learning literature. Examples include matrix multiplication actions on point clouds by permutations, rotations, and various other linear groups. Often the requirement of invariant separation is relaxed and only generic separation is required. In this case, we show that only $D+1$ invariants are required. More importantly, generic invariants are often significantly easier to compute, as we illustrate by discussing generic and full separation for weighted graphs. Finally we outline an approach for proving that separating invariants can be constructed also when the random parameters have finite precision.

This work introduces a new, distributed implementation of the Ensemble Kalman Filter (EnKF) that allows for non-sequential assimilation of large datasets in high-dimensional problems. The traditional EnKF algorithm is computationally intensive and exhibits difficulties in applications requiring interaction with the background covariance matrix, prompting the use of methods like sequential assimilation which can introduce unwanted consequences, such as dependency on observation ordering. Our implementation leverages recent advancements in distributed computing to enable the construction and use of the full model error covariance matrix in distributed memory, allowing for single-batch assimilation of all observations and eliminating order dependencies. Comparative performance assessments, involving both synthetic and real-world paleoclimatic reconstruction applications, indicate that the new, non-sequential implementation outperforms the traditional, sequential one.

The year is 2100, and humans live in underground cities and rely on AI mentors to make decisions. While the scenario sounds like a plot of a science-fiction film, it could be our reality, experts told DailyMail.com. Ed Johnson, CEO and Co-Founder of PushFar, said, 'In 2100, our lives are not just entwined with technology; they are guided, shaped, and mentored by it Below are five things that will happen by this century's mid-point - good and evil. 'Digital humans' will live among us Humanoid robots and'digital friends' will live alongside people, with robots taking on tasks including surgery and simply keeping people company. Rob Sims, co-founder and CEO of Sum Vivas, said: 'Technology will have developed to fully support digital humans without the need for instruction, educators or supporters, and companions (digital friends) will be part of everyday life.

OpenAI may grab all the headlines, but Amazon has been quietly toiling on AI across all its divisions and even using AI-powered robots in its warehouses. Now, in a bid to attract new talent, the company is launching a free program called "AI Ready," with the aim of providing generative AI training to two million people globally by 2025. Consisting of eight free courses, the classes will be available through Amazon's learning website and offered to non-Amazon employees as well. They'll teach people AI skills including the generative AI technology that powers ChatGPT and other language models. They're designed for beginners and advanced users in both tech and tech-adjacent roles.

The availability of representative datasets is an essential prerequisite for many successful artificial intelligence and machine learning models. However, in real life applications these models often encounter scenarios that are inadequately represented in the data used for training. There are various reasons for the absence of sufficient data, ranging from time and cost constraints to ethical considerations. As a consequence, the reliable usage of these models, especially in safety-critical applications, is still a tremendous challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches. Knowledge augmented machine learning approaches offer the possibility of compensating for deficiencies, errors, or ambiguities in the data, thus increasing the generalization capability of the applied models. Even more, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-driven models with existing knowledge. The identified approaches are structured according to the categories knowledge integration, extraction and conformity. In particular, we address the application of the presented methods in the field of autonomous driving.

Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context from external knowledge sources to complement the language model. However, existing retrieval augmentation techniques ignore the structural relationships between these documents. Furthermore, retrieval models are not explored much in scientific tasks, especially in regard to the faithfulness of retrieved documents. In this paper, we propose a novel structure-aware retrieval augmented language model that accommodates document structure during retrieval augmentation. We create a heterogeneous document graph capturing multiple types of relationships (e.g., citation, co-authorship, etc.) that connect documents from more than 15 scientific disciplines (e.g., Physics, Medicine, Chemistry, etc.). We train a graph neural network on the curated document graph to act as a structural encoder for the corresponding passages retrieved during the model pretraining. Particularly, along with text embeddings of the retrieved passages, we obtain structural embeddings of the documents (passages) and fuse them together before feeding them to the language model. We evaluate our model extensively on various scientific benchmarks that include science question-answering and scientific document classification tasks. Experimental results demonstrate that structure-aware retrieval improves retrieving more coherent, faithful and contextually relevant passages, while showing a comparable performance in the overall accuracy.

With the bomb ignited by ChatGPT, Transformer-based Large Language Models (LLMs) have paved a revolutionary path toward Artificial General Intelligence (AGI) and have been applied in diverse areas as knowledge bases, human interfaces, and dynamic agents. However, a prevailing limitation exists: many current LLMs, constrained by resources, are primarily pre-trained on shorter texts, rendering them less effective for longer-context prompts, commonly encountered in real-world settings. In this paper, we present a comprehensive survey focusing on the advancement of model architecture in Transformer-based LLMs to optimize long-context capabilities across all stages from pre-training to inference. We firstly delineate and analyze the problems of handling long-context input and output with the current Transformer-based models. Then, we mainly offer a holistic taxonomy to navigate the landscape of Transformer upgrades on architecture to solve these problems. Afterward, we provide the investigation on wildly used evaluation necessities tailored for long-context LLMs, including datasets, metrics, and baseline models, as well as some amazing optimization toolkits like libraries, systems, and compilers to augment LLMs' efficiency and efficacy across different stages. Finally, we further discuss the predominant challenges and potential avenues for future research in this domain. Additionally, we have established a repository where we curate relevant literature with real-time updates at https://github.com/Strivin0311/long-llms-learning.

Recent studies attempted to utilize multilayer perceptrons (MLPs) to solve semi-supervised node classification on graphs, by training a student MLP by knowledge distillation (KD) from a teacher graph neural network (GNN). While previous studies have focused mostly on training the student MLP by matching the output probability distributions between the teacher and student models during KD, it has not been systematically studied how to inject the structural information in an explicit and interpretable manner. Inspired by GNNs that separate feature transformation $T$ and propagation $\Pi$, we re-frame the KD process as enabling the student MLP to explicitly learn both $T$ and $\Pi$. Although this can be achieved by applying the inverse propagation $\Pi^{-1}$ before distillation from the teacher GNN, it still comes with a high computational cost from large matrix multiplications during training. To solve this problem, we propose Propagate & Distill (P&D), which propagates the output of the teacher GNN before KD and can be interpreted as an approximate process of the inverse propagation $\Pi^{-1}$. Through comprehensive evaluations using real-world benchmark datasets, we demonstrate the effectiveness of P&D by showing further performance boost of the student MLP.