Gopinath Chennupati

Gopinath Chennupati, Milind Rao, Gurpreet Chadha et al.

Incremental learning is one paradigm to enable model building and updating at scale with streaming data. For end-to-end automatic speech recognition (ASR) tasks, the absence of human annotated labels along with the need for privacy preserving policies for model building makes it a daunting challenge. Motivated by these challenges, in this paper we use a cloud based framework for production systems to demonstrate insights from privacy preserving incremental learning for automatic speech recognition (ILASR). By privacy preserving, we mean, usage of ephemeral data which are not human annotated. This system is a step forward for production levelASR models for incremental/continual learning that offers near real-time test-bed for experimentation in the cloud for end-to-end ASR, while adhering to privacy-preserving policies. We show that the proposed system can improve the production models significantly(3%) over a new time period of six months even in the absence of human annotated labels with varying levels of weak supervision and large batch sizes in incremental learning. This improvement is 20% over test sets with new words and phrases in the new time period. We demonstrate the effectiveness of model building in a privacy-preserving incremental fashion for ASR while further exploring the utility of having an effective teacher model and use of large batch sizes.

Guruprasad V Ramesh, Gopinath Chennupati, Milind Rao et al.

Federated Learning (FL) is a privacy-preserving paradigm, allowing edge devices to learn collaboratively without sharing data. Edge devices like Alexa and Siri are prospective sources of unlabeled audio data that can be tapped to learn robust audio representations. In this work, we bring Self-supervised Learning (SSL) and FL together to learn representations for Automatic Speech Recognition respecting data privacy constraints. We use the speaker and chapter information in the unlabeled speech dataset, Libri-Light, to simulate non-IID speaker-siloed data distributions and pre-train an LSTM encoder with the Contrastive Predictive Coding framework with FedSGD. We show that the pre-trained ASR encoder in FL performs as well as a centrally pre-trained model and produces an improvement of 12-15% (WER) compared to no pre-training. We further adapt the federated pre-trained models to a new language, French, and show a 20% (WER) improvement over no pre-training.

Ganesh Tata, Gautham Krishna Gudur, Gopinath Chennupati et al.

Calibration can reduce overconfident predictions of deep neural networks, but can calibration also accelerate training? In this paper, we show that it can when used to prioritize some examples for performing subset selection. We study the effect of popular calibration techniques in selecting better subsets of samples during training (also called sample prioritization) and observe that calibration can improve the quality of subsets, reduce the number of examples per epoch (by at least 70%), and can thereby speed up the overall training process. We further study the effect of using calibrated pre-trained models coupled with calibration during training to guide sample prioritization, which again seems to improve the quality of samples selected.

Vivswan Shah, Randy Cogill, Hanwei Yue et al.

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes: naturalness, comprehensiveness, and on-topic adherence, each rated on 5-point scales. Using ensemble-generated data from multiple LLMs, we fine-tune a 7B-parameter model and test across six diverse conversational datasets. Across 18 dataset, task settings, label-plus-explanation training outperforms label-only baselines. A central and unexpected result concerns random tokens. We replace human-written explanations with text that is syntactically incoherent yet vocabulary-aligned with the originals (e.g., shuffled or bag-of-words variants). Despite lacking semantics, these pseudo-explanations still improve accuracy over label-only training and often narrow much of the gap to true explanations. The effect persists across datasets and training seeds, indicating that gains arise less from meaning than from structure: the extra token budget encourages richer intermediate computation and acts as a regularizer that reduces over-confident shortcuts. Internal analyses support this view: explanation-augmented models exhibit higher activation entropy in intermediate layers alongside sharper predictive mass at the output layer, consistent with increased deliberation before decision. Overall, explanation-augmented fine-tuning, whether with genuine rationales or carefully constructed random token sequences, improves accuracy and reliability for LLM classification while clarifying how token-level scaffolding shapes computation during inference.

Sunil Thulasidasan, Tanmoy Bhattacharya, Jeff Bilmes et al.

We introduce a novel method to combat label noise when training deep neural networks for classification. We propose a loss function that permits abstention during training thereby allowing the DNN to abstain on confusing samples while continuing to learn and improve classification performance on the non-abstained samples. We show how such a deep abstaining classifier (DAC) can be used for robust learning in the presence of different types of label noise. In the case of structured or systematic label noise -- where noisy training labels or confusing examples are correlated with underlying features of the data-- training with abstention enables representation learning for features that are associated with unreliable labels. In the case of unstructured (arbitrary) label noise, abstention during training enables the DAC to be used as an effective data cleaner by identifying samples that are likely to have label noise. We provide analytical results on the loss function behavior that enable dynamic adaption of abstention rates based on learning progress during training. We demonstrate the utility of the deep abstaining classifier for various image classification tasks under different types of label noise; in the case of arbitrary label noise, we show significant improvements over previously published results on multiple image benchmarks. Source code is available at https://github.com/thulas/dac-label-noise

Hamdy Abdelkhalik, Shamminuj Aktar, Yehia Arafa et al.

Recent years have seen the adoption of Machine Learning (ML) techniques to predict the performance of large-scale applications, mostly at a coarse level. In contrast, we propose to use ML techniques for performance prediction at a much finer granularity, namely at the Basic Block (BB) level, which are single entry, single exit code blocks that are used for analysis by the compilers to break down a large code into manageable pieces. We extrapolate the basic block execution counts of GPU applications and use them for predicting the performance for large input sizes from the counts of smaller input sizes. We train a Poisson Neural Network (PNN) model using random input values as well as the lowest input values of the application to learn the relationship between inputs and basic block counts. Experimental results show that the model can accurately predict the basic block execution counts of 16 GPU benchmarks. We achieve an accuracy of 93.5% in extrapolating the basic block counts for large input sets when trained on smaller input sets and an accuracy of 97.7% in predicting basic block counts on random instances. In a case study, we apply the ML model to CUDA GPU benchmarks for performance prediction across a spectrum of applications. We use a variety of metrics for evaluation, including global memory requests and the active cycles of tensor cores, ALU, and FMA units. Results demonstrate the model's capability of predicting the performance of large datasets with an average error rate of 0.85% and 0.17% for global and shared memory requests, respectively. Additionally, to address the utilization of the main functional units in Ampere architecture GPUs, we calculate the active cycles for tensor cores, ALU, FMA, and FP64 units and achieve an average error of 2.3% and 10.66% for ALU and FMA units while the maximum observed error across all tested applications and units reaches 18.5%.

Sunil Thulasidasan, Sushil Thapa, Sayera Dhaubhadel et al.

Refraining from confidently predicting when faced with categories of inputs different from those seen during training is an important requirement for the safe deployment of deep learning systems. While simple to state, this has been a particularly challenging problem in deep learning, where models often end up making overconfident predictions in such situations. In this work we present a simple, but highly effective approach to deal with out-of-distribution detection that uses the principle of abstention: when encountering a sample from an unseen class, the desired behavior is to abstain from predicting. Our approach uses a network with an extra abstention class and is trained on a dataset that is augmented with an uncurated set that consists of a large number of out-of-distribution (OoD) samples that are assigned the label of the abstention class; the model is then trained to learn an effective discriminator between in and out-of-distribution samples. We compare this relatively simple approach against a wide variety of more complex methods that have been proposed both for out-of-distribution detection as well as uncertainty modeling in deep learning, and empirically demonstrate its effectiveness on a wide variety of of benchmarks and deep architectures for image recognition and text classification, often outperforming existing approaches by significant margins. Given the simplicity and effectiveness of this method, we propose that this approach be used as a new additional baseline for future work in this domain.

Nasrin Akhter, Gopinath Chennupati, Hristo Djidjev et al.

Identifying one or more biologically-active/native decoys from millions of non-native decoys is one of the major challenges in computational structural biology. The extreme lack of balance in positive and negative samples (native and non-native decoys) in a decoy set makes the problem even more complicated. Consensus methods show varied success in handling the challenge of decoy selection despite some issues associated with clustering large decoy sets and decoy sets that do not show much structural similarity. Recent investigations into energy landscape-based decoy selection approaches show promises. However, lack of generalization over varied test cases remains a bottleneck for these methods. We propose a novel decoy selection method, ML-Select, a machine learning framework that exploits the energy landscape associated with the structure space probed through a template-free decoy generation. The proposed method outperforms both clustering and energy ranking-based methods, all the while consistently offering better performance on varied test-cases. Moreover, ML-Select shows promising results even for the decoy sets consisting of mostly low-quality decoys. ML-Select is a useful method for decoy selection. This work suggests further research in finding more effective ways to adopt machine learning frameworks in achieving robust performance for decoy selection in template-free protein structure prediction.

Sayera Dhaubhadel, Jamaludin Mohd-Yusof, Kumkum Ganguly et al.

Safe deployment of deep learning systems in critical real world applications requires models to make very few mistakes, and only under predictable circumstances. In this work, we address this problem using an abstaining classifier that is tuned to have $>$95% accuracy, and then identify the determinants of abstention using LIME. Essentially, we are training our model to learn the attributes of pathology reports that are likely to lead to incorrect classifications, albeit at the cost of reduced sensitivity. We demonstrate an abstaining classifier in a multitask setting for classifying cancer pathology reports from the NCI SEER cancer registries on six tasks of interest. For these tasks, we reduce the classification error rate by factors of 2--5 by abstaining on 25--45% of the reports. For the specific task of classifying cancer site, we are able to identify metastasis, reports involving lymph nodes, and discussion of multiple cancer sites as responsible for many of the classification mistakes, and observe that the extent and types of mistakes vary systematically with cancer site (e.g., breast, lung, and prostate). When combining across three of the tasks, our model classifies 50% of the reports with an accuracy greater than 95% for three of the six tasks\edit, and greater than 85% for all six tasks on the retained samples. Furthermore, we show that LIME provides a better determinant of classification than measures of word occurrence alone. By combining a deep abstaining classifier with feature identification using LIME, we are able to identify concepts responsible for both correctness and abstention when classifying cancer sites from pathology reports. The improvement of LIME over keyword searches is statistically significant, presumably because words are assessed in context and have been identified as a local determinant of classification.

Manish Bhattarai, Gopinath Chennupati, Erik Skau et al.

The era of exascale computing opens new venues for innovations and discoveries in many scientific, engineering, and commercial fields. However, with the exaflops also come the extra-large high-dimensional data generated by high-performance computing. High-dimensional data is presented as multidimensional arrays, aka tensors. The presence of latent (not directly observable) structures in the tensor allows a unique representation and compression of the data by classical tensor factorization techniques. However, the classical tensor methods are not always stable or they can be exponential in their memory requirements, which makes them not suitable for high-dimensional tensors. Tensor train (TT) is a state-of-the-art tensor network introduced for factorization of high-dimensional tensors. TT transforms the initial high-dimensional tensor in a network of three-dimensional tensors that requires only a linear storage. Many real-world data, such as, density, temperature, population, probability, etc., are non-negative and for an easy interpretation, the algorithms preserving non-negativity are preferred. Here, we introduce a distributed non-negative tensor-train and demonstrate its scalability and the compression on synthetic and real-world big datasets.

Atanu Barai, Gopinath Chennupati, Nandakishore Santhi et al.

Performance modeling of parallel applications on multicore computers remains a challenge in computational co-design due to the complex design of multicore processors including private and shared memory hierarchies. We present a Scalable Analytical Shared Memory Model to predict the performance of parallel applications that runs on a multicore computer and shares the same level of cache in the hierarchy. This model uses a computationally efficient, probabilistic method to predict the reuse distance profiles, where reuse distance is a hardware architecture-independent measure of the patterns of virtual memory accesses. It relies on a stochastic, static basic block-level analysis of reuse profiles measured from the memory traces of applications ran sequentially on small instances rather than using a multi-threaded trace. The results indicate that the hit-rate predictions on the shared cache are accurate.

Sunil Thulasidasan, Gopinath Chennupati, Jeff Bilmes et al.

Mixup~\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to implement, it has been shown to be a surprisingly effective method of data augmentation for image classification: DNNs trained with mixup show noticeable gains in classification performance on a number of image classification benchmarks. In this work, we discuss a hitherto untouched aspect of mixup training -- the calibration and predictive uncertainty of models trained with mixup. We find that DNNs trained with mixup are significantly better calibrated -- i.e., the predicted softmax scores are much better indicators of the actual likelihood of a correct prediction -- than DNNs trained in the regular fashion. We conduct experiments on a number of image classification architectures and datasets -- including large-scale datasets like ImageNet -- and find this to be the case. Additionally, we find that merely mixing features does not result in the same calibration benefit and that the label smoothing in mixup training plays a significant role in improving calibration. Finally, we also observe that mixup-trained DNNs are less prone to over-confident predictions on out-of-distribution and random-noise data. We conclude that the typical overconfidence seen in neural networks, even on in-distribution data is likely a consequence of training with hard labels, suggesting that mixup be employed for classification tasks where predictive uncertainty is a significant concern.

Gopinath Chennupati

Ant Colony Optimization (ACO) has been applied in supervised learning in order to induce classification rules as well as decision trees, named Ant-Miners. Although these are competitive classifiers, the stability of these classifiers is an important concern that owes to their stochastic nature. In this paper, to address this issue, an acclaimed machine learning technique named, ensemble of classifiers is applied, where an ACO classifier is used as a base classifier to prepare the ensemble. The main trade-off is, the predictions in the new approach are determined by discovering a group of models as opposed to the single model classification. In essence, we prepare multiple models from the randomly replaced samples of training data from which, a unique model is prepared by aggregating the models to test the unseen data points. The main objective of this new approach is to increase the stability of the Ant-Miner results there by improving the performance of ACO classification. We found that the ensemble Ant-Miners significantly improved the stability by reducing the classification error on unseen data.