The rise of machine learning (ML) systems has exacerbated their carbon footprint due to increased capabilities and model sizes. However, there is scarce knowledge on how the carbon footprint of ML models is actually measured, reported, and evaluated. In light of this, the paper aims to analyze the measurement of the carbon footprint of 1,417 ML models and associated datasets on Hugging Face, which is the most popular repository for pretrained ML models. The goal is to provide insights and recommendations on how to report and optimize the carbon efficiency of ML models. The study includes the first repository mining study on the Hugging Face Hub API on carbon emissions. This study seeks to answer two research questions: (1) how do ML model creators measure and report carbon emissions on Hugging Face Hub?, and (2) what aspects impact the carbon emissions of training ML models? The study yielded several key findings. These include a stalled proportion of carbon emissions-reporting models, a slight decrease in reported carbon footprint on Hugging Face over the past 2 years, and a continued dominance of NLP as the main application domain. Furthermore, the study uncovers correlations between carbon emissions and various attributes such as model size, dataset size, and ML application domains. These results highlight the need for software measurements to improve energy reporting practices and promote carbon-efficient model development within the Hugging Face community. In response to this issue, two classifications are proposed: one for categorizing models based on their carbon emission reporting practices and another for their carbon efficiency. The aim of these classification proposals is to foster transparency and sustainable model development within the ML community.

Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes a description of the standard Transformer architecture, a series of model refinements, and common applications. Given that Transformers and related deep learning techniques might be evolving in ways we have never seen, we cannot dive into all the model details or cover all the technical areas. Instead, we focus on just those concepts that are helpful for gaining a good understanding of Transformers and their variants. We also summarize the key ideas that impact this field, thereby yielding some insights into the strengths and limitations of these models.

Two-tower models are a prevalent matching framework for recommendation, which have been widely deployed in industrial applications. The success of two-tower matching attributes to its efficiency in retrieval among a large number of items, since the item tower can be precomputed and used for fast Approximate Nearest Neighbor (ANN) search. However, it suffers two main challenges, including limited feature interaction capability and reduced accuracy in online serving. Existing approaches attempt to design novel late interactions instead of dot products, but they still fail to support complex feature interactions or lose retrieval efficiency. To address these challenges, we propose a new matching paradigm named SparCode, which supports not only sophisticated feature interactions but also efficient retrieval. Specifically, SparCode introduces an all-to-all interaction module to model fine-grained query-item interactions. Besides, we design a discrete code-based sparse inverted index jointly trained with the model to achieve effective and efficient model inference. Extensive experiments have been conducted on open benchmark datasets to demonstrate the superiority of our framework. The results show that SparCode significantly improves the accuracy of candidate item matching while retaining the same level of retrieval efficiency with two-tower models. Our source code will be available at MindSpore/models.

Transformers have become the gold standard for many natural language processing tasks and, in particular, for multi-hop question answering (MHQA). This task includes processing a long document and reasoning over the multiple parts of it. The landscape of MHQA approaches can be classified into two primary categories. The first group focuses on extracting supporting evidence, thereby constraining the QA model's context to predicted facts. Conversely, the second group relies on the attention mechanism of the long input encoding model to facilitate multi-hop reasoning. However, attention-based token representations lack explicit global contextual information to connect reasoning steps. To address these issues, we propose GEMFormer, a two-stage method that first collects relevant information over the entire document to the memory and then combines it with local context to solve the task. Our experimental results show that fine-tuning a pre-trained model with memory-augmented input, including the most certain global elements, improves the model's performance on three MHQA datasets compared to the baseline. We also found that the global explicit memory contains information from supporting facts required for the correct answer.

In recent years, the field of Deep Learning has seen many disruptive and impactful advancements. Given the increasing complexity of deep neural networks, the need for efficient hardware accelerators has become more and more pressing to design heterogeneous HPC platforms. The design of Deep Learning accelerators requires a multidisciplinary approach, combining expertise from several areas, spanning from computer architecture to approximate computing, computational models, and machine learning algorithms. Several methodologies and tools have been proposed to design accelerators for Deep Learning, including hardware-software co-design approaches, high-level synthesis methods, specific customized compilers, and methodologies for design space exploration, modeling, and simulation. These methodologies aim to maximize the exploitable parallelism and minimize data movement to achieve high performance and energy efficiency. This survey provides a holistic review of the most influential design methodologies and EDA tools proposed in recent years to implement Deep Learning accelerators, offering the reader a wide perspective in this rapidly evolving field. In particular, this work complements the previous survey proposed by the same authors in [203], which focuses on Deep Learning hardware accelerators for heterogeneous HPC platforms.

DisCoCat [1, 2] (Categorical Compositional Distributional) models are structure-preserving maps which send grammatical types to vector spaces and grammatical structures to linear maps. Concretely, the meaning of words is given by tensors with shapes induced by their grammatical types; the meaning of sentences is given by contracting the tensor networks induced by their grammatical structure. String diagrams provide an intuitive graphical language to visualise and reason formally about the evaluation of DisCoCat models; which can be formalised in terms of functors F: G Vect from the category generated by a formal grammar G to the monoidal category Vect of vector spaces and linear maps with the tensor product [3, 2.5]. Although this functorial definition applies equally to any kind of formal grammar, most of the DisCoCat literature focuses on pregroup grammars and more generally on categorial grammars such as the Lambek calculus [4, 5] and combinatory categorial grammars (CCG) [6]. In that case, G is a closed monoidal category and the DisCoCat models F: G Vect map grammatical structures to the closed structure of Vect in a canonical way. In practice, this means that once the meaning of each word is computed from a dataset, the meaning of any new grammatical sentence can be computed automatically from its grammatical structure.

We investigate the molecular gene expressions studies and public databases for disease modelling using Probabilistic Graphical Models and Bayesian Inference. A case study on Spinal Muscle Atrophy Genome-Wide Association Study results is modelled and analyzed. The genes up and down-regulated in two stages of the disease development are linked to prior knowledge published in the public domain and co-expressions network is created and analyzed. The Molecular Pathways triggered by these genes are identified. The Bayesian inference posteriors distributions are estimated using a variational analytical algorithm and a Markov chain Monte Carlo sampling algorithm. Assumptions, limitations and possible future work are concluded.

Hyperparameter Optimization (HPO) of Deep Learning-based models tends to be a compute resource intensive process as it usually requires to train the target model with many different hyperparameter configurations. We show that integrating model performance prediction with early stopping methods holds great potential to speed up the HPO process of deep learning models. Moreover, we propose a novel algorithm called Swift-Hyperband that can use either classical or quantum support vector regression for performance prediction and benefit from distributed High Performance Computing environments. This algorithm is tested not only for the Machine-Learned Particle Flow model used in High Energy Physics, but also for a wider range of target models from domains such as computer vision and natural language processing. Swift-Hyperband is shown to find comparable (or better) hyperparameters as well as using less computational resources in all test cases.

Prompt-based learning has been widely applied in many low-resource NLP tasks such as few-shot scenarios. However, this paradigm has been shown to be vulnerable to backdoor attacks. Most of the existing attack methods focus on inserting manually predefined templates as triggers in the pre-training phase to train the victim model and utilize the same triggers in the downstream task to perform inference, which tends to ignore the transferability and stealthiness of the templates. In this work, we propose a novel approach of TARGET (Template-trAnsfeRable backdoor attack aGainst prompt-basEd NLP models via GPT4), which is a data-independent attack method. Specifically, we first utilize GPT4 to reformulate manual templates to generate tone-strong and normal templates, and the former are injected into the model as a backdoor trigger in the pre-training phase. Then, we not only directly employ the above templates in the downstream task, but also use GPT4 to generate templates with similar tone to the above templates to carry out transferable attacks. Finally we have conducted extensive experiments on five NLP datasets and three BERT series models, with experimental results justifying that our TARGET method has better attack performance and stealthiness compared to the two-external baseline methods on direct attacks, and in addition achieves satisfactory attack capability in the unseen tone-similar templates.

The problem of firebreak placement is crucial for fire prevention, and its effectiveness at landscape scale will depend on their ability to impede the progress of future wildfires. To provide an adequate response, it is therefore necessary to consider the stochastic nature of fires, which are highly unpredictable from ignition to extinction. Thus, the placement of firebreaks can be considered a stochastic optimization problem where: (1) the objective function is to minimize the expected cells burnt of the landscape; (2) the decision variables being the location of firebreaks; and (3) the random variable being the spatial propagation/behavior of fires. In this paper, we propose a solution approach for the problem from the perspective of simulation-based optimization (SbO), where the objective function is not available (a black-box function), but can be computed (and/or approximated) by wildfire simulations. For this purpose, Genetic Algorithm and GRASP are implemented. The final implementation yielded favorable results for the Genetic Algorithm, demonstrating strong performance in scenarios with medium to high operational capacity, as well as medium levels of stochasticity