AAAI 2025 论文列表

Maternal mortality remains a significant global public health challenge. One promising approach to reducing maternal deaths occurring during facility-based childbirth is through early warning systems, which require the consistent monitoring of mothers' vital signs after giving birth. Wireless vital sign monitoring devices offer a labor-efficient solution for continuous monitoring, but their scarcity raises the critical question of how to allocate them most effectively. We devise an allocation algorithm for this problem by modeling it as a variant of the popular Restless Multi-Armed Bandit (RMAB) paradigm. In doing so, we identify and address novel, previously unstudied constraints unique to this domain, which render previous approaches for RMABs unsuitable and significantly increase the complexity of the learning and planning problem. To overcome these challenges, we adopt the popular Proximal Policy Optimization (PPO) algorithm from reinforcement learning to learn an allocation policy by training a policy and value function network. We demonstrate in simulations that our approach outperforms the best heuristic baseline by up to a factor of 4.

Diffusion models (DMs) have attracted attention in generative modeling due to their ability to produce high-quality, diverse outputs by progressively adding noise to data and then denoising it. However, DMs are computationally intensive due to their iterative nature, requiring numerous forward passes and high-precision operations, making them less efficient for resource-constrained environments. Recent efforts to reduce these computational demands using quantization show promise by converting high-precision parameters to lower precision, but they face challenges unique to DMs, particularly in addressing cross-timestep error propagation in the iterative process. In this paper, we analyze cross-timestep error propagation in quantized DMs, revealing that previous methods focusing only on reducing noise estimation discrepancies are insufficient. Instead, we introduce Cross-Timestep Error Correction (CTEC), where the quantized model not only approximates the full-precision model but also corrects errors from the previous timestep. A distillation method is applied to learn this correction process effectively. We conduct extensive experiments on unconditional image generation with LSUN-Churches and LSUN-Bedrooms, as well as conditional image generation with ImageNet. Our findings demonstrate the effectiveness of our method in significantly reducing accumulated quantization errors across timesteps within the quantized diffusion process. This enhancement enables the generation of high-quality images, even when constrained by reduced bitwidths.

Weakly supervised person search aims to detect and match individuals using only bounding box annotations jointly. The existing methods mainly alternate between the clustering stage and the training stage, where the former is responsible for instance level label allocation tasks and the latter needs to undertake proposal level label allocation tasks. In the clustering phase, the conventional use of the DBSCAN algorithm for clustering pedestrian instance features often neglects key contextual information such as scene context and relative positioning of individuals. During the training phase, the Region Proposal Network assigns labels based on the MaxIoU, which tends to produce locally ambiguous labels. Finally, the proposals updated to the memory bank with extensive background information tend to interfere with the task of pseudo-label generation. To address these issues, this paper proposes an Optimizing Label Assignment (OLA) for weakly supervised person search. Firstly, in the clustering phase, Context Aware Clustering is introduced to integrate contextual information and constraints, enhancing the accuracy of clustering. Secondly, in the training phase, we adopt Prototype Matching based on Optimal Transport theory to optimize label distribution from a global perspective. Furthermore, we propose Dual Memory Bank Enhancement that effectively enhances the accuracy of label assignment. Extensive experiments conducted on the CUHK-SYSU and PRW datasets demonstrate that our method achieves state-of-the-art performance in weakly supervised person search.

Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One aspect that has been overlooked so far is that existing methods learn motion clues from all pixels rather than focusing on the target human body, making them easily misled and disrupted by unimportant information such as background changes or movements of other people. Additionally, while the current Transformer-based pose estimation methods has demonstrated impressive performance with global modeling, they struggle with local context perception and precise positional identification. In this paper, we try to tackle these challenges from three aspects: (1) We propose a bilayer Human-Keypoint Mask module that performs coarse-to-fine visual token refinement, which gradually zooms in on the target human body and keypoints while masking out unimportant figure regions. (2) We further introduce a novel deformable cross attention mechanism and a bidirectional separation strategy to adaptively aggregate spatial and temporal motion clues from constrained surrounding contexts. (3) We mathematically formulate the deformable cross attention, constraining that the model focuses solely on the regions centered at the target person body. Empirically, our method achieves state-of-the-art performance on three large-scale benchmark datasets. A remarkable highlight is that our method achieves an 84.8 mean Average Precision (mAP) on the challenging wrist joint, which significantly outperforms the 81.5 mAP achieved by the current state-of-the-art method on the PoseTrack2017 dataset.

A key strategy in societal adaptation to climate change is using alert systems to prompt preventative action and reduce the adverse health impacts of extreme heat events. This paper implements and evaluates reinforcement learning (RL) as a tool to optimize the effectiveness of such systems. Our contributions are threefold. First, we introduce a new publicly available RL environment enabling the evaluation of the effectiveness of heat alert policies to reduce heat-related hospitalizations. The rewards model is trained from a comprehensive dataset of historical weather, Medicare health records, and socioeconomic/geographic features. We use scalable Bayesian techniques tailored to the low-signal effects and spatial heterogeneity present in the data. The transition model uses real historical weather patterns enriched by a data augmentation mechanism based on climate region similarity. Second, we use this environment to evaluate standard RL algorithms in the context of heat alert issuance. Our analysis shows that policy constraints are needed to improve RL's initially poor performance. Third, a post-hoc contrastive analysis provides insight into scenarios where our modified heat alert-RL policies yield significant gains/losses over the current National Weather Service alert policy in the United States.

Antibiotic Resistance (AR) is a critical global health challenge that necessitates the development of cost-effective, efficient, and accurate diagnostic tools. Given the genetic basis of AR, techniques such as Polymerase Chain Reaction (PCR) that target specific resistance genes offer a promising approach for predictive diagnostics using a limited set of key genes. This study introduces GenoARM, a novel framework that integrates reinforcement learning (RL) with transformer-based models to optimize the selection of PCR gene tests and improve AR predictions, leveraging observed metadata for improved accuracy. In our evaluation, we developed several high-performing baselines and compared them using publicly available datasets derived from real-world bacterial samples representing multiple clinically relevant pathogens. The results show that all evaluated methods achieve strong and reliable performance when metadata is not utilized. When metadata is introduced and the number of selected genes increases, GenoARM demonstrates superior performance due to its capacity to approximate rewards for unseen and sparse combinations. Overall, our framework represents a major advancement in optimizing diagnostic tools for AR in clinical settings.

The neural tangent kernel (NTK) has emerged as an important tool in recent years, both for developing a theoretical understanding of deep learning as well as for various applications. Even though recursive closed form expressions have been derived for computing the NTK, these become computationally expensive as the complexity of a network increases. Recent papers have looked at reducing this complexity using various sketching techniques along with random features. Building on these techniques, we propose an additional optimization step which results in better approximation of the NTK.

Previous research has shown that constraining the gradient of loss function w.r.t. model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed optimal threshold for gradient clipping through validation data to obtain the desired robustness against noise. However, this common practice overlooks the dynamic distribution of gradients from both clean and noisy-labeled samples at different stages of training, significantly limiting the model capability to adapt to the variable nature of gradients throughout the training process. To address this issue, we propose a simple yet effective approach called Optimized Gradient Clipping (OGC), which dynamically adjusts the clipping threshold based on the ratio of noise gradients to clean gradients after clipping, estimated by modeling the distributions of clean and noisy samples. This approach allows us to modify the clipping threshold at each training step, effectively controlling the influence of noise gradients. Additionally, we provide statistical analysis to certify the noise-tolerance ability of OGC. Our extensive experiments across various types of label noise, including symmetric, asymmetric, instance-dependent, and real-world noise, demonstrate the effectiveness of our approach.

Deep neural networks have become foundational to advancements in multiple domains, including recommendation systems, natural language processing, and so on. Despite their successes, these models often contain incompatible parameters that can be underutilized or detrimental to model performance, particularly when faced with specific, varying data distributions. Existing research excels in removing such parameters or merging the outputs of multiple different pretrained models. However, the former focuses on efficiency rather than performance, while the latter requires several times more computing and storage resources to support inference. In this paper, we set the goal to explicitly improve these incompatible parameters by leveraging the complementary strengths of different models, thereby directly enhancing the models without any additional parameters. Specifically, we propose Compatibility-aware Knowledge Integration (CKI), which consists of Parameter Compatibility Assessment and Parameter Splicing, which are used to evaluate the knowledge content of multiple models and integrate the knowledge into one model, respectively. The integrated model can be used directly for inference or for further fine-tuning. Extensive experiments on various recommendation and language datasets show that CKI can effectively optimize incompatible parameters under multiple tasks and settings to break through the training limit of the original model without increasing the inference cost.

We introduce a novel method for assessing agent teamwork based on their spatial coordination. Our approach models the influence of spatial proximity on team formation and sustained spatial dominance over adversaries using a Multi-agent Markov Decision Process. We develop an algorithm to derive efficient teamwork strategies by combining Monte Carlo Tree Search and linear programming. When applied to team defence in football (soccer) using real-world data, our approach reduces opponent threat by 21%, outperforming optimised individual behaviour by 6%. Additionally, our model enhances the predictive accuracy of future attack locations and provides deeper insights compared to existing teamwork models that do not explicitly consider the spatial dynamics of teamwork.

The centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to ϵ-optimally solving decentralized partially observable Markov decision processes. However, scalability remains a significant issue. This paper presents a novel and more scalable alternative, namely the sequential-move centralized training for decentralized execution. This paradigm further pushes the applicability of the Bellman’s principle of optimality, raising three new properties. First, it allows a central planner to reason upon sufficient sequential-move statistics instead of prior simultaneous-move ones. Next, it proves that ϵ-optimal value functions are piecewise linear and convex in such sufficient sequential-move statistics. Finally, it drops the complexity of the backup operators from double exponential to polynomial at the expense of longer planning horizons. Besides, it makes it easy to use single-agent methods, e.g., SARSA algorithm enhanced with these findings, while still preserving convergence guarantees. Experiments on two- as well as many-agent domains from the literature against ϵ-optimal simultaneous-move solvers confirm the superiority of our novel approach. This paradigm opens the door for efficient planning and reinforcement learning methods for multi-agent systems.

Even though data annotation is extremely important for interpretability, research, and development of artificial intelligence solutions, annotating data remains costly. Research efforts such as active learning or few-shot learning alleviate the cost by increasing sample efficiency, yet the problem of annotating data more quickly has received comparatively little attention. Leveraging a predictor has been shown to reduce annotation cost in practice but has not been theoretically considered. We ask the following question: to annotate a binary classification dataset with N samples, can the annotator answer less than N yes/no questions? Framing this question-and-answer (Q&A) game as an optimal encoding problem, we find a positive answer given by the Huffman encoding of the possible labelings. Unfortunately, the algorithm is computationally intractable even for small dataset sizes. As a practical method, we propose to minimize a cost function a few steps ahead, similarly to lookahead minimization in optimal control. This solution is analyzed, compared with the optimal one, and evaluated using several synthetic and real-world datasets. The method allows a significant improvement (23-86%) in the annotation efficiency of real-world datasets.

Autonomous robots are essential for navigating and collecting data in hazardous environments where human intervention is impractical. Current methods often result in inefficiencies, missed high-quality imagery, and inadequate coverage in critical areas such as environmental monitoring, disaster response, and medical diagnostics. The absence of intelligent viewpoint selection leads to redundant data and poor image quality, limiting robotic effectiveness. This research proposes a framework that utilizes reinforcement learning and information-theoretic approaches to optimize viewpoint selection, aiming to enhance data collection efficiency and image quality while ensuring safety. This work has the potential to transform industries reliant on precise visual data and significantly improve medical robotics, enabling better diagnostics and patient care.

Optimal control problems (OCPs) involve finding a control function for a dynamical system such that a cost functional is optimized. It is central to physical systems in both academia and industry. In this paper, we propose a novel instance-solution control operator perspective, which solves OCPs in a one-shot manner without direct dependence on the explicit expression of dynamics or iterative optimization processes. The control operator is implemented by a new neural operator architecture named Neural Adaptive Spectral Method (NASM), a generalization of classical spectral methods. We theoretically validate the perspective and architecture by presenting the approximation error bounds of NASM for the control operator. Experiments on synthetic environments and a real-world dataset verify the effectiveness and efficiency of our approach, including substantial speedup in running time, and high-quality in- and out-of-distribution generalization.

Computing an optimal classification tree that provably maximizes training performance within a given size limit, is NP-hard, and in practice, most state-of-the-art methods do not scale beyond computing optimal trees of depth three. Therefore, most methods rely on a coarse binarization of continuous features to maintain scalability. We propose a novel algorithm that optimizes trees directly on the continuous feature data using dynamic programming with branch-and-bound. We develop new pruning techniques that eliminate many sub-optimal splits in the search when similar to previously computed splits and we provide an efficient subroutine for computing optimal depth-two trees. Our experiments demonstrate that these techniques improve runtime by one or more orders of magnitude over state-of-the-art optimal methods and improve test accuracy by 5% over greedy heuristics.

In perpetual voting, multiple decisions are made at different moments in time. Taking the history of previous decisions into account allows us to satisfy properties such as proportionality over periods of time. In this paper, we consider the following question: is there a perpetual approval voting method that guarantees that no voter is dissatisfied too many times? We identify a sufficient condition on voter behavior ---which we call 'bounded conflicts' condition---under which a sublinear growth of dissatisfaction is possible. We provide a tight upper bound on the growth of dissatisfaction under bounded conflicts, using techniques from Kolmogorov complexity. We also observe that the approval voting with binary choices mimics the machine learning setting of prediction with expert advice. This allows us to present a voting method with sublinear guarantees on dissatisfaction under bounded conflicts, based on the standard techniques from prediction with expert advice.

The predominant setting in classic auction theory considers bidders as utility maximizers (UMs), who aim to maximize quasi-linear utility functions. Recent autobidding strategies in online advertising have sparked interest in auction design with value maximizers (VMs), who aim to maximize the total value obtained. In this work, we investigate revenue-maximizing auction design for selling a single item to a mix of UMs and VMs. Crucially, we assume the UM/VM type is private information of a bidder. This shift to a multi-parameter domain complicates the design of incentive compatible mechanisms. Under this setting, we first characterize the optimal auction structure for auctions with a single bidder. We observe that the optimal auction moves gradually from a first-price auction to a Myerson auction as the probability of the bidder being a UM increases from 0 to 1. We also extend our study to multi-bidder setting and present an algorithm for deriving the optimal lookahead auction with multiple mixed types of bidders.

Social norms are standards of behaviour common in a society. However, when agents make decisions without considering how others are impacted, norms can emerge that lead to the subjugation of certain agents. We present RAWL·E, a method to create ethical norm-learning agents. RAWL·E agents operationalise maximin, a fairness principle from Rawlsian ethics, in their decision-making processes to promote ethical norms by balancing societal well-being with individual goals. We evaluate RAWL·E agents in simulated harvesting scenarios. We find that norms emerging in RAWL·E agent societies enhance social welfare, fairness, and robustness, and yield higher minimum experience compared to those that emerge in agent societies that do not implement Rawlsian ethics.

Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained; 2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding Network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples.