This paper proposes a unified theoretical framework based on the Kolmogorov-Arnold representation theorem and kernel methods. By analyzing the mathematical relationship among kernels, B-spline basis functions in Kolmogorov-Arnold Networks (KANs) and the inner product operation in self-attention mechanisms, we establish a kernel-based feature fitting framework that unifies the two models as linear combinations of kernel functions. Under this framework, we propose a low-rank Pseudo-Multi-Head Self-Attention module (Pseudo-MHSA), which reduces the parameter count of traditional MHSA by nearly 50\%. Furthermore, we design a Gaussian kernel multi-head self-attention variant (Gaussian-MHSA) to validate the effectiveness of nonlinear kernel functions in feature extraction. Experiments on the CIFAR-10 dataset demonstrate that Pseudo-MHSA model achieves performance comparable to the ViT model of the same dimensionality under the MAE framework and visualization analysis reveals their similarity of multi-head distribution patterns. Our code is publicly available.

The evolution of speech technology has been spurred by the rapid increase in dataset sizes. Traditional speech models generally depend on a large amount of labeled training data, which is scarce for low-resource languages. This paper presents GigaSpeech 2, a large-scale, multi-domain, multilingual speech recognition corpus. It is designed for low-resource languages and does not rely on paired speech and text data. GigaSpeech 2 comprises about 30,000 hours of automatically transcribed speech, including Thai, Indonesian, and Vietnamese, gathered from unlabeled YouTube videos. We also introduce an automated pipeline for data crawling, transcription, and label refinement. Specifically, this pipeline uses Whisper for initial transcription and TorchAudio for forced alignment, combined with multi-dimensional filtering for data quality assurance. A modified Noisy Student Training is developed to further refine flawed pseudo labels iteratively, thus enhancing model performance. Experimental results on our manually transcribed evaluation set and two public test sets from Common Voice and FLEURS confirm our corpus's high quality and broad applicability. Notably, ASR models trained on GigaSpeech 2 can reduce the word error rate for Thai, Indonesian, and Vietnamese on our challenging and realistic YouTube test set by 25% to 40% compared to the Whisper large-v3 model, with merely 10% model parameters. Furthermore, our ASR models trained on Gigaspeech 2 yield superior performance compared to commercial services. We believe that our newly introduced corpus and pipeline will open a new avenue for low-resource speech recognition and significantly facilitate research in this area.

The COVID-19 pandemic has posed a heavy burden to the healthcare system worldwide and caused huge social disruption and economic loss. Many deep learning models have been proposed to conduct clinical predictive tasks such as mortality prediction for COVID-19 patients in intensive care units using Electronic Health Record (EHR) data. Despite their initial success in certain clinical applications, there is currently a lack of benchmarking results to achieve a fair comparison so that we can select the optimal model for clinical use. Furthermore, there is a discrepancy between the formulation of traditional prediction tasks and real-world clinical practice in intensive care. To fill these gaps, we propose two clinical prediction tasks, Outcome-specific length-of-stay prediction and Early mortality prediction for COVID-19 patients in intensive care units. The two tasks are adapted from the naive length-of-stay and mortality prediction tasks to accommodate the clinical practice for COVID-19 patients. We propose fair, detailed, open-source data-preprocessing pipelines and evaluate 17 state-of-the-art predictive models on two tasks, including 5 machine learning models, 6 basic deep learning models and 6 deep learning predictive models specifically designed for EHR data. We provide benchmarking results using data from two real-world COVID-19 EHR datasets. One dataset is publicly available without needing any inquiry and another dataset can be accessed on request. We provide fair, reproducible benchmarking results for two tasks. We deploy all experiment results and models on an online platform. We also allow clinicians and researchers to upload their data to the platform and get quick prediction results using our trained models. We hope our efforts can further facilitate deep learning and machine learning research for COVID-19 predictive modeling.

We present a novel approach to evaluate the performance of interpretability methods for time series classification, and propose a new strategy to assess the similarity between domain experts and machine data interpretation. The novel approach leverages a new family of synthetic datasets and introduces new interpretability evaluation metrics. The approach addresses several common issues encountered in the literature, and clearly depicts how well an interpretability method is capturing neural network's data usage, providing a systematic interpretability evaluation framework. The new methodology highlights the superiority of Shapley Value Sampling and Integrated Gradients for interpretability in time-series classification tasks.

Graph Neural Network (GNN) research is rapidly growing thanks to the capacity of GNNs to learn representations from graph-structured data. However, centralizing a massive amount of real-world graph data for GNN training is prohibitive due to user-side privacy concerns, regulation restrictions, and commercial competition. Federated learning (FL), a trending distributed learning paradigm, aims to solve this challenge while preserving privacy. Despite recent advances in vision and language domains, there is no suitable platform for the federated training of GNNs. To this end, we introduce FedGraphNN, an open research federated learning system and a benchmark to facilitate GNN-based FL research. FedGraphNN is built on a unified formulation of federated GNNs and supports commonly used datasets, GNN models, FL algorithms, and flexible APIs. We also contribute a new molecular dataset, hERG, to promote research exploration. Our experimental results present significant challenges in federated GNN training: federated GNNs perform worse in most datasets with a non-I.I.D split than centralized GNNs; the GNN model that attains the best result in the centralized setting may not hold its advantage in the federated setting. These results imply that more research efforts are needed to unravel the mystery behind federated GNN training. Moreover, our system performance analysis demonstrates that the FedGraphNN system is computationally affordable to most research labs with limited GPUs. We maintain the source code at https://github.com/FedML-AI/FedGraphNN.

Optimizing a neural network's performance is a tedious and time taking process, this iterative process does not have any defined solution which can work for all the problems. Optimization can be roughly categorized into - Architecture and Hyperparameter optimization. Many algorithms have been devised to address this problem. In this paper we introduce a neural network architecture (Deep Genetic Network) which will optimize its parameters during training based on its fitness. Deep Genetic Net uses genetic algorithms along with deep neural networks to address the hyperparameter optimization problem, this approach uses ideas like mating and mutation which are key to genetic algorithms which help the neural net architecture to learn to optimize its hyperparameters by itself rather than depending on a person to explicitly set the values. Using genetic algorithms for this problem proved to work exceptionally well when given enough time to train the network. The proposed architecture is found to work well in optimizing hyperparameters in affine, convolutional and recurrent layers proving to be a good choice for conventional supervised learning tasks.

Many recently trained neural networks employ large numbers of parameters to achieve good performance. One may intuitively use the number of parameters required as a rough gauge of the difficulty of a problem. But how accurate are such notions? How many parameters are really needed? In this paper we attempt to answer this question by training networks not in their native parameter space, but instead in a smaller, randomly oriented subspace. We slowly increase the dimension of this subspace, note at which dimension solutions first appear, and define this to be the intrinsic dimension of the objective landscape. The approach is simple to implement, computationally tractable, and produces several suggestive conclusions. Many problems have smaller intrinsic dimensions than one might suspect, and the intrinsic dimension for a given dataset varies little across a family of models with vastly different sizes. This latter result has the profound implication that once a parameter space is large enough to solve a problem, extra parameters serve directly to increase the dimensionality of the solution manifold. Intrinsic dimension allows some quantitative comparison of problem difficulty across supervised, reinforcement, and other types of learning where we conclude, for example, that solving the inverted pendulum problem is 100 times easier than classifying digits from MNIST, and playing Atari Pong from pixels is about as hard as classifying CIFAR-10. In addition to providing new cartography of the objective landscapes wandered by parameterized models, the method is a simple technique for constructively obtaining an upper bound on the minimum description length of a solution. A byproduct of this construction is a simple approach for compressing networks, in some cases by more than 100 times.