Association for the Advancement of Artificial Intelligence: AAAI Publications
Not a member yet
26155 research outputs found
Sort by
Efficient Federated Learning via Clients-to-Server Knowledge Distillation (Student Abstract)
No full textTo diminish the substantial communication costs incurred by federated learning during the training of the global model and enhance the model update efficiency across both clients and server domains, we have integrated knowledge distillation into the federated learning framework. This integration has led to the development of a novel approach termed ClientsToServerKDFL, which streamlines the distillation process by directly transferring model insights from clients to the server for computational learning without the need for extensive computations across numerous clients. This iterative process ensures model accuracy and curtails communication expenses. Experimental data analysis has validated the efficacy of this algorithm
A High-Efficiency Federated Learning Method Using Complementary Pruning for D2D Communication (Student Abstract)
No full textIn federated learning, frequent parameter transmission between clients and the server results in significant communication overhead, particularly due to redundancy within the parameters. To address this issue, we propose a Complementary Pruning for Device-to-Device Communication (FedCPD) method. This approach effectively reduces the amount of transmitted parameters by applying complementary pruning techniques on both the server and clients. Additionally, we decrease the communication frequency between clients and the server by employing chain updates among clients (i.e., device-to-device communication). We conducted experiments on the MNIST, FMNIST, CIFAR-10, and CIFAR-100 datasets, and the results demonstrate that our method significantly reduces communication costs while improving model accuracy
Does Knowing More Make You Easier to Trick? Adversarial Robustness of Multi-Target Regression
No full textFollowing the rapid rise of deep learning (DL) and generative artificial intelligence (GenAI), it is imperative that we gain a better understanding of how these machine learning (ML) systems actually learn. What information are DL models retaining from the training data? What reasoning capabilities do these models have? In my proposed project, I aim to tackle these pressing questions through use of an adversarial lens
Knowledge-Infused Learning for Developing a Mental Health Diagnostic Copilot in Healthcare Systems
No full textHealthcare diagnostics, especially in underserved communities, faces critical gaps in accessibility and accuracy. African Americans experience significant disparities in mental health care, often receiving delayed or inadequate treatment. This research proposes a diagnostic copilot, an AI-powered assistant designed to work alongside healthcare professionals. Using Knowledge-Infused Learning (KIL) and multi-turn conversations, the system integrates clinical knowledge and patient input to deliver actionable, explainable diagnoses in real-time. By engaging with both patients and clinicians, the copilot aims to reduce disparities, enhance trust, and improve diagnostic accuracy in mental health care
SDAS: Semantic Data Acquisition System for Minimizing Redundancy and Maximizing Diversity
No full textIn this paper, we propose SDAS, a new motion data assessment and storage system designed to acquire new motion data with reduced redundancy and maximizing diversity. SDAS collects data in the field, retrieves the most similar data from the database in real-time, and provides visualization tools that allow for the comparison of differences between the capture data and the stored data. Through this system, researchers can efficiently build and manage a database. The demonstration video is available at https://youtu.be/vqW0uMDnZTw
TRACE-CS: A Synergistic Approach to Explainable Course Scheduling Using LLMs and Logic
No full textWe present TRACE-cs, a novel hybrid system that combines symbolic reasoning with large language models (LLMs) to address contrastive queries in scheduling problems. TRACE-cs leverages SAT solving techniques to encode scheduling constraints and generate explanations for user queries, while utilizing an LLM to process the user queries into logical clauses as well as refine the explanations generated by the symbolic solver to natural language sentences. By integrating these components, our approach demonstrates the potential of combining symbolic methods with LLMs to create explainable AI agents with correctness guarantees
PRIORITY2REWARD: Incorporating Healthworker Preferences for Resource Allocation Planning
No full textIn this paper, we present PRIORITY2REWARD a Large Language Model (LLM) based application which incorporates health worker preferences for resource allocation planning in public health programs. LLMs are increasingly used to design reward functions based on human preferences in Reinforcement Learning problems. We focus on LLM-designed rewards for Restless Multi-Armed Bandits, a framework for allocating limited resources among agents. In the context of public health, our approach empowers grassroots health workers to tailor automated allocation decisions to community needs. We showcase a simulated application of PRIORITY2REWARD for a large-scale mobile health program in India. The tool allows health workers to enter natural language preferences and leverages LLMs to search for reward functions aligned with the preference. Our tool then dynamically showcases how the LLM generated reward function modifies the policy outcomes with respect to different demographic groups in the population. This can help inform policy implementation at a community level
CODE: Confident Ordinary Differential Editing
No full textConditioning image generation facilitates seamless editing and the creation of photorealistic images. However, conditioning on noisy or Out-of-Distribution (OoD) images poses significant challenges, particularly in balancing fidelity to the input and realism of the output. We introduce Confident Ordinary Differential Editing (CODE), a novel approach for image synthesis that effectively handles OoD guidance images. Utilizing a diffusion model as a generative prior, CODE enhances images through score-based updates along the probability-flow Ordinary Differential Equation (ODE) trajectory. This method requires no task-specific training, handcrafted modules, or assumptions, and is compatible with any diffusion model. Positioned at the intersection of conditional image generation and blind image restoration, CODE operates in a fully blind manner, relying solely on a pre-trained generative model. Our method introduces an alternative approach to blind restoration: instead of targeting a specific ground truth image based on assumptions about the underlying corruption, CODE aims to increase the likelihood of the input image while maintaining fidelity. This results in the most probable in-distribution image around the input. Our contributions are twofold. First, CODE introduces a novel editing method based on ODE providing enhanced control, realism, and fidelity compared to SDE-based counterpart. Second, we introduce a confidence interval-based clipping method, which improves CODE’s effectiveness by allowing it to disregard certain pixels or information, thus enhancing the restoration process in a blind manner. Experimental results demonstrate CODE’s effectiveness over existing methods, particularly in scenarios involving severe degradation or OoD inputs
Towards Learnable Anchor for Deep Multi-View Clustering
No full textDeep multi-view clustering incorporating graph learning has presented tremendous potential. Most methods encounter costly square time consumption w.r.t. data size. Theoretically, anchor-based graph learning can alleviate this limitation, but related deep models mainly rely on manual discretization approaches to select anchors, which indicates that 1) the anchors are fixed during model training and 2) they may deviate from the true cluster distribution. Consequently, the unreliable anchors may corrupt clustering results. In this paper, we propose the Deep Multi-view Anchor Clustering (DMAC) model that performs clustering in linear time. Concretely, the initial anchors are intervened by the positive-incentive noise sampled from Gaussian distribution, such that they can be optimized with a newly designed anchor learning loss, which promotes a clear relationship between samples and anchors. Afterwards, anchor graph convolution is devised to model the cluster structure formed by the anchors, and the mutual information maximization loss is built to provide cross-view clustering guidance. In this way, the learned anchors can better represent clusters. With the optimal anchors, the full sample graph is calculated to derive a discriminative embedding for clustering. Extensive experiments on several datasets demonstrate the superior performance and efficiency of DMAC compared to state-of-the-art competitors
Are Expressive Models Truly Necessary for Offline RL?
No full textAmong various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL problem as a sequential modeling task, therefore bypassing the notoriously difficult credit assignment challenge of value learning in conventional RL paradigm. Sequential modeling, however, requires capturing accurate dynamics across long horizons in trajectory data to ensure reasonable policy performance. To meet this requirement, leveraging large, expressive models has become a popular choice in recent literature, which, however, comes at the cost of significantly increased computation and inference latency. Contradictory yet promising, we reveal that lightweight models as simple as shallow 2-layer MLPs, can also enjoy accurate dynamics consistency and significantly reduced sequential modeling errors against large expressive models by adopting a simple recursive planning scheme: recursively planning coarse-grained future sub-goals based on current and target information, and then executes the action with a goal-conditioned policy learned from data relabeled with these sub-goal ground truths. We term our method as Recursive Skip-Step Planning (RSP). Simple yet effective, RSP enjoys great efficiency improvements thanks to its lightweight structure, and substantially outperforms existing methods, reaching new SOTA performances on the D4RL benchmark, especially in multi-stage long-horizon tasks