Graph contrastive learning attracts/disperses node representations for similar/dissimilar node pairs under some notion of similarity. It may be combined with a low-dimensional embedding of nodes to preserve intrinsic and structural properties of a graph. In this paper, we extend the celebrated Laplacian Eigenmaps with contrastive learning, and call them COntrastive Laplacian EigenmapS (COLES). Starting from a GAN-inspired contrastive formulation, we show that the Jensen-Shannon divergence underlying many contrastive graph embedding models fails under disjoint positive and negative distributions, which may naturally emerge during sampling in the contrastive setting. In contrast, we demonstrate analytically that COLES essentially minimizes a surrogate of Wasserstein distance, which is known to cope well under disjoint distributions. Moreover, we show that the loss of COLES belongs to the family of so-called block-contrastive losses, previously shown to be superior compared to pair-wise losses typically used by contrastive methods. We show on popular benchmarks/backbones that COLES offers favourable accuracy/scalability compared to DeepWalk, GCN, Graph2Gauss, DGI and GRACE baselines.

Graph contrastive learning attracts/disperses node representations for similar/dissimilar node pairs under some notion of similarity.

To address the need for a more comprehensive evaluation of French Natural Language Understanding (NLU), we introduce COLE, a new benchmark composed of 23 diverse task covering a broad range of NLU capabilities, including sentiment analysis, paraphrase detection, grammatical judgment, and reasoning, with a particular focus on linguistic phenomena relevant to the French language. We benchmark 94 large language models (LLM), providing an extensive analysis of the current state of French NLU. Our results highlight a significant performance gap between closed- and open-weights models and identify key challenging frontiers for current LLMs, such as zero-shot extractive question-answering (QA), fine-grained word sense disambiguation, and understanding of regional language variations. We release COLE as a public resource to foster further progress in French language modelling.

Graph contrastive learning attracts/disperses node representations for similar/dissimilar node pairs under some notion of similarity.

Artificial intelligence (AI) is producing hyperrealistic "digital twins" of politicians, celebrities, pornographic material, and more – leaving victims of deepfake technology struggling to determine legal recourse. Former CIA agent and cybersecurity expert Dr. Eric Cole told Fox News Digital that poor online privacy practices and people's willingness to post their information publicly on social media leaves them susceptible to AI deepfakes. "The cat's already out of the bag," he said. "They have our pictures, they know our kids, they know our family. They know where we live. And now, with AI, they're able to take all that data about who we are, what we look like, what we do, and how we act, and basically be able to create a digital twin," Cole continued.

This paper investigates approximation-theoretic aspects of the in-context learning capability of the transformers in representing a family of noisy linear dynamical systems. Our first theoretical result establishes an upper bound on the approximation error of multi-layer transformers with respect to an $L^2$-testing loss uniformly defined across tasks. This result demonstrates that transformers with logarithmic depth can achieve error bounds comparable with those of the least-squares estimator. In contrast, our second result establishes a non-diminishing lower bound on the approximation error for a class of single-layer linear transformers, which suggests a depth-separation phenomenon for transformers in the in-context learning of dynamical systems. Moreover, this second result uncovers a critical distinction in the approximation power of single-layer linear transformers when learning from IID versus non-IID data.

Graph contrastive learning attracts/disperses node representations for similar/dissimilar node pairs under some notion of similarity. It may be combined with a low-dimensional embedding of nodes to preserve intrinsic and structural properties of a graph. COLES, a recent graph contrastive method combines traditional graph embedding and negative sampling into one framework. COLES in fact minimizes the trace difference between the within-class scatter matrix encapsulating the graph connectivity and the total scatter matrix encapsulating negative sampling. In this paper, we propose a more essential framework for graph embedding, called Generalized Laplacian EigeNmaps (GLEN), which learns a graph representation by maximizing the rank difference between the total scatter matrix and the within-class scatter matrix, resulting in the minimum class separation guarantee.

Yet realizing measurable business value from AI-powered applications requires a new game plan. Rather, the time is now for organizations to modernize their infrastructure, processes, and application architectures using cloud native technologies to stay competitive. Today's organizations exist in an era of geopolitical shifts, growing competition, supply chain disruptions, and evolving consumer preferences. AI applications can help by supporting innovation, but only if they have the flexibility to scale when needed. Fortunately, by modernizing applications, organizations can achieve the agile development, scalability, and fast compute performance needed to support rapid innovation and accelerate the delivery of AI applications. David Harmon, director of software development for AMD says companies, "really want to make sure that they can migrate their current [environment] and take advantage of all the hardware changes as much as possible."