Krishnan Raghavan

Continual learning is a challenge for models with static architecture, as they fail to adapt to when data distributions evolve across tasks. We introduce a mathematical framework that jointly models architecture and weights in a Sobolev space, enabling a rigorous investigation into the role of neural network architecture in continual learning and its effect on the forgetting loss. We derive necessary conditions for the continual learning solution and prove that learning only model weights is insufficient to mitigate catastrophic forgetting under distribution shifts. Consequently, we prove that by learning the architecture and weights simultaneously at each task, we can reduce catastrophic forgetting. To learn weights and architecture simultaneously, we formulate continual learning as a bilevel optimization problem: the upper level selects an optimal architecture for a given task, while the lower level computes optimal weights via dynamic programming over all tasks. To solve the upper level problem, we introduce a derivative-free direct search algorithm to determine the optimal architecture. Once found, we must transfer knowledge from the current architecture to the optimal one. However, the optimal architecture will result in a weights parameter space different from the current architecture (i.e., dimensions of weights matrices will not match). To bridge the dimensionality gap, we develop a low-rank transfer mechanism to map knowledge across architectures of mismatched dimensions. Empirical studies across regression and classification problems, including feedforward, convolutional, and graph neural networks, demonstrate that learning the optimal architecture and weights simultaneously yields substantially improved performance (up to two orders of magnitude), reduced forgetting, and enhanced robustness to noise compared with static architecture approaches.

The stability-plasticity dilemma, closely related to a neural network's (NN) capacity-its ability to represent tasks-is a fundamental challenge in continual learning (CL). Within this context, we introduce CL's effective model capacity (CLEMC) that characterizes the dynamic behavior of the stability-plasticity balance point. We develop a difference equation to model the evolution of the interplay between the NN, task data, and optimization procedure. We then leverage CLEMC to demonstrate that the effective capacity-and, by extension, the stability-plasticity balance point is inherently non-stationary. We show that regardless of the NN architecture or optimization method, a NN's ability to represent new tasks diminishes when incoming task distributions differ from previous ones. We conduct extensive experiments to support our theoretical findings, spanning a range of architectures-from small feedforward network and convolutional networks to medium-sized graph neural networks and transformer-based large language models with millions of parameters.

Large Language Models (LLMs) based on transformer architectures excel at internet-scale tasks. However, real-world scientific scenarios—such as synthetic chemistry laboratories and autonomous experimental setups—typically involve incremental data generation in batches as new chemical reactions are conducted, unlike static, large-scale datasets. Motivated by scaling laws—which suggest that larger models are increasingly prone to catastrophic forgetting when learning from sequentially arriving data— we present a case study investigating continual learning for chemical reaction yield prediction using Mistral-7B, a 7.3-billion-parameter open-weight LLM. We first establish a baseline by evaluating model performance on the Suzuki Coupling Reactions dataset using both supervised full fine-tuning and Low-Rank Adaptation (LoRA), showing competitive yield prediction accuracy. To mimic real-world conditions, we adopt a task-incremental learning framework in which the model incrementally learns a new task group defined by unique pairs of reactants. This sequential learning setup enables us to directly assess the model’s ability to retain prior knowledge. We demonstrate that when the model is trained within this sequential learning paradigm with traditional procedures, it exhibits significant loss of prior knowledge, a phenomenon known as catastrophic forgetting in the continual learning community—an under-recognized challenge in the chemistry community. To understand this challenge, we first model the problem of continual learning and investigate the source of forgetting, subsequently, we incorporate experience replay to maintain near-baseline performance across tasks without forgetting. These results highlight the importance of integrating continual learning strategies into LLM-based chemical modeling pipelines, particularly as future experimental platforms increasingly generate non-stationary reaction data.

Anomaly detection in computational workflows is critical for ensuring system reliability and security. However, traditional rule-based methods struggle to detect novel anomalies. This paper leverages large language models (LLMs) for workflow anomaly detection by exploiting their ability to learn complex data patterns. Two approaches are investigated: 1) supervised fine-tuning (SFT), where pre-trained LLMs are fine-tuned on labeled data for sentence classification to identify anomalies, and 2) in-context learning (ICL) where prompts containing task descriptions and examples guide LLMs in few-shot anomaly detection without fine-tuning. The paper evaluates the performance, efficiency, generalization of SFT models, and explores zero-shot and few-shot ICL prompts and interpretability enhancement via chain-of-thought prompting. Experiments across multiple workflow datasets demonstrate the promising potential of LLMs for effective anomaly detection in complex executions.

A computational workflow, also known as workflow, consists of tasks that are executed in a certain order to attain a specific computational campaign. Computational workflows are commonly employed in science domains, such as physics, chemistry, genomics, to complete large-scale experiments in distributed and heterogeneous computing environments. However, running computations at such a large scale makes the workflow applications prone to failures and performance degradation, which can slowdown, stall, and ultimately lead to workflow failure. Learning how these workflows behave under normal and anomalous conditions can help us identify the causes of degraded performance and subsequently trigger appropriate actions to resolve them. However, learning in such circumstances is a challenging task because of the large volume of high-quality historical data needed to train accurate and reliable models. Generating such datasets not only takes a lot of time and effort but it also requires a lot of resources to be devoted to data generation for training purposes. Active learning is a promising approach to this problem. It is an approach where the data is generated as required by the machine learning model and thus it can potentially reduce the training data needed to derive accurate models. In this work, we present an active learning approach that is supported by an experimental framework, Poseidon-X, that utilizes a modern workflow management system and two cloud testbeds. We evaluate our approach using three computational workflows. For one workflow we run an end-to-end live active learning experiment, for the other two we evaluate our active learning algorithms using pre-captured data traces provided by the Flow-Bench benchmark. Our findings indicate that active learning not only saves resources, but it also improves the accuracy of the detection of anomalies.

Computational Fluid Dynamics (CFD) is used in the design and optimization of gas turbines and many other industrial/ scientific applications. However, the practical use is often limited by the high computational cost, and the accurate resolution of near-wall flow is a significant contributor to this cost. Machine learning (ML) and other data-driven methods can complement existing wall models. Nevertheless, training these models is bottlenecked by the large computational effort and memory footprint demanded by back-propagation. Recent work has presented alternatives for computing gradients of neural networks where a separate forward and backward sweep is not needed and storage of intermediate results between sweeps is not required because an unbiased estimator for the gradient is computed in a single forward sweep. In this paper, we discuss the application of this approach for training a subgrid wall model that could potentially be used as a surrogate in wall-bounded flow CFD simulations to reduce the computational overhead while preserving predictive accuracy.

Anomaly detection is the task of identifying abnormal behavior of a system. Anomaly detection in computational workflows is of special interest because of its wide implications in various domains such as cybersecurity, finance, and social networks. However, anomaly detection in computational workflows~(often modeled as graphs) is a relatively unexplored problem and poses distinct challenges. For instance, when anomaly detection is performed on graph data, the complex interdependency of nodes and edges, the heterogeneity of node attributes, and edge types must be accounted for. Although the use of graph neural networks can help capture complex inter-dependencies, the scarcity of labeled anomalous examples from workflow executions is still a significant challenge. To address this problem, we introduce an autoencoder-driven self-supervised learning~(SSL) approach that learns a summary statistic from unlabeled workflow data and estimates the normal behavior of the computational workflow in the latent space. In this approach, we combine generative and contrastive learning objectives to detect outliers in the summary statistics. We demonstrate that by estimating the distribution of normal behavior in the latent space, we can outperform state-of-the-art anomaly detection methods on our benchmark datasets.

Continual learning~(CL) is a field concerned with learning a series of inter-related task with the tasks typically defined in the sense of either regression or classification. In recent years, CL has been studied extensively when these tasks are defined using Euclidean data -- data, such as images, that can be described by a set of vectors in an n-dimensional real space. However, the literature is quite sparse, when the data corresponding to a CL task is nonEuclidean -- data , such as graphs, point clouds or manifold, where the notion of similarity in the sense of Euclidean metric does not hold. For instance, a graph is described by a tuple of vertices and edges and similarities between two graphs is not well defined through a Euclidean metric. Due to this fundamental nature of the data, developing CL for nonEuclidean data presents several theoretical and methodological challenges. In particular, CL for graphs requires explicit modelling of nonstationary behavior of vertices and edges and their effects on the learning problem. Therefore, in this work, we develop a adaptive dynamic programming viewpoint for CL with graphs. In this work, we formulate a two-player sequential game between the act of learning new tasks~(generalization) and remembering previously learned tasks~(forgetting). We prove mathematically the existence of a solution to the game and demonstrate convergence to the solution of the game. Finally, we demonstrate the efficacy of our method on a number of graph benchmarks with a comprehensive ablation study while establishing state-of-the-art performance.