AAAI 2025 论文列表

Recent advancements in Neural Combinatorial Optimization (NCO) have shown promise in solving routing problems like the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) without handcrafted designs. Research in this domain has explored two primary categories of methods: iterative and non-iterative. While non-iterative methods struggle to generate near-optimal solutions directly, iterative methods simplify the task by learning local search steps. However, existing iterative methods are often limited by restricted neighborhood searches, leading to suboptimal results. To address this limitation, we propose a novel approach that extends the search to larger neighborhoods by learning a destroy-and-repair strategy. Specifically, we introduce a Destroy-and-Repair framework based on Hyper-Graphs (DRHG). This framework reduces consecutive intact edges to hyper-edges, allowing the model to pay more attention to the destroyed part and decrease the complexity of encoding all nodes. Experiments demonstrate that DRHG achieves state-of-the-art performance on TSP with up to 10,000 nodes and shows strong generalization to real-world TSPLib and CVRPLib problems.

Spatial-temporal graph modeling is challenging due to the diverse node interactions across spatial and temporal dimensions. Recent studies typically adopt Graph Neural Networks (GNNs) to perform node-level aggregation at different time steps, acting as a series of low-pass graph spectral filters, for node interaction modeling. However, these filters, confined to the spatial dimension, are ill-suited for processing signals of nodes with inherent spatial-temporal interdependencies. Moreover, oversimplified low-pass filtering fails to fully exploit information from diverse node interactions. To address these issues, we propose a Spatial-Temporal Spectral Graph Neural Network (STSGNN), which designs specialized two-dimensional (2-D) graph spectral filters for comprehensive spatial-temporal graph modeling. First, based on the normalized Laplacian spectrum of spatial and temporal graphs, we extend the existing graph spectral theory from a univariate spatial dimension to a bivariate spatial-temporal dimension through a 2-D Discrete Graph Fourier Transform (2-D DGFT). Then, we leverage the bivariate Bernstein polynomial approximation, with learned basis coefficients, to design 2-D filters with specialized spectral properties for unified spatial-temporal signal filtering. Finally, the filtered signals, with refined spatial-temporal representations, are fed into well-designed pyramidal gated convolution modules to acquire multiple ranges of spatial-temporal dependencies. Experiments on traffic and meteorological prediction tasks demonstrate that STSGNN achieves state-of-the-art performance. Additionally, we visualize the 2-D filters learned from inputs with distinct spatial-temporal characteristics to enhance the model's interpretability.

The growing impact of AI on various fields, including art, highlights the importance of integrating AI learning into art education. This work investigates whether traditional art lessons can be adapted to meaningfully incorporate AI, focusing on its application to art-making practices. We adapted a character design activity to incorporate AI at different stages, such as using AI for creating references, getting feedback, visual design, animation, and personality design. We developed a character design learning activity which was supplemented by a code notebook and a front-end character design tool. 39 middle and high school students participated in this activity during two in-person Art and AI workshops. Analysis of creative outputs, knowledge surveys, and classroom discussions showed that students showed significant shifts in their understanding of AI as a creative collaborator, their art making practice, and their confidence with using AI tools. Learners demonstrated different creative styles while adopting AI into their character design. This approach demonstrates the potential for integrating AI into art lessons and offers a scalable framework for other non-CS subjects.

Distributionally robust optimization tackles out-of-sample issues like overfitting and distribution shifts by adopting an adversarial approach over a range of possible data distributions, known as the ambiguity set. To balance conservatism and accuracy, these sets must include realistic probability distributions by leveraging information from the nominal distribution. Assuming that nominal distributions arise from a structural causal model with a directed acyclic graph G and structural equations, previous methods such as adapted and G-causal optimal transport have only utilized causal graph information in designing ambiguity sets. In this work, we propose incorporating structural equations, which include causal graph information, to enhance ambiguity sets, resulting in more realistic distributions. We introduce structural causal optimal transport and its associated ambiguity set, demonstrating their advantages and connections to previous methods. A key benefit of our approach is a relaxed version, where a regularization term replaces the complex causal constraints, enabling an efficient algorithm via difference-of-convex programming to solve structural causal optimal transport. We also show that when structural information is absent and must be estimated, our approach remains effective and provides finite sample guarantees. Lastly, we address the radius of ambiguity sets, illustrating how our method overcomes the curse of dimensionality in optimal transport problems, achieving faster shrinkage with dimension-free order.

Spatial-aware image editing focuses on modifying the position and size of elements within a given image. However, previous works still struggle with maintaining background harmony in the original editing areas, as well as preserving the initial identity of the edited elements, making it difficult to achieve complex multi-object editing in a single pass. In this paper, we aim to perform flexible spatial editing in a simple yet straightforward manner. We propose to inpaint the background first and develop a two-stage multi-layered latent diffusion framework to edit each element independently. Specifically, we design a key-masking self-attention scheme alongside artifact suppression to achieve background inpainting within the denoising process, leveraging the powerful generative capabilities of the Latent Diffusion Model, Stable Diffusion XL-1.0. The latent decomposition and fusion framework is capable of unifying various spatial-aware operations, including removal, resizing, relocation, flipping, addition, camera panning, zooming out, occlusion-aware editing, and cross-image editing. Experiments demonstrate the superior inpainting quality for object removal, along with enhanced versatility and higher precision in spatial-aware editing achieved by our method.

Students with learning disabilities (LDs) face significant challenges in key academic areas such as reading comprehension, cognitive organization, self-expression, mathematics, and handwriting. These difficulties increase their susceptibility to discrimination and mental health related issues. Although existing studies have primarily focused on AI’s diagnostic capabilities, there is limited research examining how Generative AI (GenAI) can be utilized to produce measurable learning outcomes and enhance learning experiences for students with LDs. Moreover, GenAI is increasingly gaining prominence in educational settings. Therefore, the relationship between GenAI tools, LDs, and instructional methods needs to be further examined. This research aims to develop a comprehensive theoretical framework for helping design and implement tools specifically tailored to the unique needs of students with LDs. A prototype based on this framework will be implemented in selected educational settings to assess its effectiveness in improving learning outcomes and providing targeted support to students with LDs. The prototype will provide mobile phone integration to ensure scalability and enhance educational accessibility. The expected findings will contribute to the promotion of more inclusive learning environments for students with LDs.

Transferable neural architecture search (TNAS) has been introduced to design efficient neural architectures for multiple tasks, to enhance the practical applicability of NAS in real-world scenarios. In TNAS, architectural knowledge accumulated in previous search processes is reused to warm up the architecture search for new tasks. However, existing TNAS methods still search in an extensive search space, necessitating the evaluation of numerous architectures. To overcome this challenge, this work proposes a novel transfer paradigm, i.e., design principle transfer. In this work, the linguistic description of various structural components' effects on architectural performance is termed design principles. They are learned from established architectures and then can be reused to reduce the search space tasks by discarding unpromising architectures. Searching in the refined search space can boost both the search performance and efficiency for new NAS tasks. To this end, a large language model (LLM)-assisted design principle transfer (LAPT) framework is devised. In LAPT, LLM is applied to automatically reason the design principles from a set of given architectures, and then a principle adaptation method is applied to refine these principles progressively based on the search results. Experimental results demonstrate that LAPT can beat the state-of-the-art TNAS methods on most tasks and achieve comparable performance on the remainder.

Generative document retrieval is a novel retrieval framework, which represents documents as identifiers (DocID) and retrieves documents by generating DocIDs. It has the advantage of end-to-end optimization over traditional retrieval methods and has attracted much research interest. Nonetheless, the development of efficient and precise DocIDs for document representation remains a pertinent issue within the field. Existing methods for designing DocIDs tend to consider only the relevance of DocIDs to the corresponding documents, while neglecting the ability of the DocIDs to distinguish the corresponding documents from similar ones, which is crucial for the retrieval task. In this paper, we design learnable descriptive and discriminative document Identifiers (D2-DocID) for Generative Retrieval and propose the paired retrieval model D2Gen. The D2-DocID is semantically similar to the corresponding documents (descriptive) and is able to distinguish similar documents (discriminative) in the corpus, thus enhancing retrieval performance. We use a contrastive learning assisted generative retrieval task to enable the model to understand the document and then complete the generative retrieval. We then design a DocID selection method to select DocIDs based on the retrieval model's understanding of the documents. Our experimental results on the MS MARCO and NQ320k dataset illustrate the effectiveness of the approach.

Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth estimation as a direct transport between image and depth distributions. We are the first to explore flow matching in this field, and we demonstrate that its interpolation trajectories enhance both training and sampling efficiency while preserving high performance. While generative models typically require extensive training data, we mitigate this dependency by integrating external knowledge from a pre-trained image diffusion model, enabling effective transfer even across differing objectives. To further boost our model performance, we employ synthetic data and utilize image-depth pairs generated by a discriminative model on an in-the-wild image dataset. As a generative model, our model can reliably estimate depth confidence, which provides an additional advantage. Our approach achieves competitive zero-shot performance on standard benchmarks of complex natural scenes while improving sampling efficiency and only requiring minimal synthetic data for training.

In this paper, we study the challenging problem of simultaneously removing haze and estimating depth from real monocular hazy videos. These tasks are inherently complementary: enhanced depth estimation improves dehazing via the atmospheric scattering model (ASM), while superior dehazing contributes to more accurate depth estimation through the brightness consistency constraint (BCC). To tackle these intertwined tasks, we propose a novel depth-centric learning framework that integrates the ASM model with the BCC constraint. Our key idea is that both ASM and BCC rely on a shared depth estimation network. This network simultaneously exploits adjacent dehazed frames to enhance depth estimation via BCC and uses the refined depth cues to more effectively remove haze through ASM. Additionally, we leverage a non-aligned clear video and its estimated depth to independently regularize the dehazing and depth estimation networks. This is achieved by designing two discriminator networks: D_MFIR enhances high-frequency details in dehazed videos, and D_MDR reduces the occurrence of black holes in low-texture regions. Extensive experiments demonstrate that the proposed method outperforms current state-of-the-art techniques in both video dehazing and depth estimation tasks, especially in real-world hazy scenes.

Depression can be reflected by long-term human spatio-temporal facial behaviours. While human face videos recorded in real-world usually have long and variable lengths, existing video-based depression assessment approaches frequently re-sample/down-sample such videos to short and equal-length videos, or split each video into several equal-length segments, where segment-level spatio-temporal facial behaviours are suppressed as a vector-style representations for RNN-based long-term (video-level) modelling. Both strategies lead to crucial information loss and distortion. In this paper, we propose a novel graph-style data structure called Matrixial Graph and an effective Matrixial Graph Neural Network (MGNN) for face video-based depression assessment, which can directly and end-to-end model long-term depression-specific spatio-temporal facial cues from variable-length videos without resampling/splitting videos or suppressing video segments to vectors. Importantly, the nodes in our matrixial graph are capable of including matrices of different shapes, and thus nodes of a matrix graph can directly represent all frame-level 2D facial feature maps (or images themselves) of an entire video regardless of its length. Then, our MGNN is the first GNN that can jointly process matrixial graphs containing varying numbers of nodes, which further learns matrix-style edge features, thereby facilitating to explicit model video-level multi-scale spatio-temporal facial behaviours among matrixial graph nodes for depression assessment. Experiments show that the explicit spatio-temporal modeling on 2D facial feature maps, facilitated by our matrixial graph/MGNN, provided significant benefits, leading our approach to achieve new state-of-the-art performances on AVEC2013 and AVEC2014 datasets with large advantages.

Given an unweighted, undirected, and simple graph, the Densest k-Subgraph (DkS) problem aims to find a subgraph of k vertices that has the maximum average induced degree. In this paper, we consider an equivalent reformulation of the DkS problem via diagonal loading. On relaxing the combinatorial constraint of the reformulated problem, we show that the resulting non-convex, continuous relaxation is tight under certain conditions by leveraging an extension of the Motzkin-Straus theorem. We utilize two projection-free approaches to solve the relaxed problem: one based on the Frank-Wolfe algorithm and the other on explicit constraint parameterization. We compare their performance to state-of-the-art baselines across various benchmarks. Our empirical results show that the Frank-Wolfe-based algorithm proposed in this paper outperforms existing baselines in terms of subgraph density and computational complexity.

In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly favored for its effectiveness in large foundation models, as it streamlines transfer learning costs and optimizes hardware utilization. However, the current PET methods are mainly designed for single-modal optimization. While some pioneering studies have undertaken preliminary explorations, they still remain at the level of aligned encoders (e.g., CLIP) and lack exploration of misaligned encoders. These methods show sub-optimal performance with misaligned encoders, as they fail to effectively align the multimodal features during fine-tuning. In this paper, we introduce DETRIS, a parameter-efficient tuning framework designed to enhance low-rank visual feature propagation by establishing dense interconnections between each layer and all preceding layers, which enables effective cross-modal feature interaction and adaptation to misaligned encoders. We also suggest using text adapters to improve textual features. Our simple yet efficient approach greatly surpasses state-of-the-art methods with 0.9% to 1.8% backbone parameter updates, evaluated on challenging benchmarks.

In the field of audio-visual learning, most research tasks focus exclusively on short videos. This paper focuses on the more practical Dense Audio-Visual Event Localization (DAVEL) task, advancing audio-visual scene understanding for longer, untrimmed videos. This task seeks to identify and temporally pinpoint all events simultaneously occurring in both audio and visual streams. Typically, each video encompasses dense events of multiple classes, which may overlap on the timeline, each exhibiting varied durations. Given these challenges, effectively exploiting the audio-visual relations and the temporal features encoded at various granularities becomes crucial. To address these challenges, we introduce a novel CCNet, comprising two core modules: the Cross-Modal Consistency Collaboration (CMCC) and the Multi-Temporal Granularity Collaboration (MTGC). Specifically, the CMCC module contains two branches: a cross-modal interaction branch and a temporal consistency-gated branch. The former branch facilitates the aggregation of consistent event semantics across modalities through the encoding of audio-visual relations, while the latter branch guides one modality's focus to pivotal event-relevant temporal areas as discerned in the other modality. The MTGC module includes a coarse-to-fine collaboration block and a fine-to-coarse collaboration block, providing bidirectional support among coarse- and fine-grained temporal features. Extensive experiments on the UnAV-100 dataset validate our module design, resulting in a new state-of-the-art performance in dense audio-visual event localization.

We propose denoising diffusion variational inference (DDVI), a black-box variational inference algorithm for latent variable models which relies on diffusion models as flexible approximate posteriors. Specifically, our method introduces an expressive class of diffusion-based variational posteriors that perform iterative refinement in latent space; we train these posteriors with a novel regularized evidence lower bound (ELBO) on the marginal likelihood inspired by the wake-sleep algorithm. Our method is easy to implement (it fits a regularized extension of the ELBO), is compatible with black-box variational inference, and outperforms alternative classes of approximate posteriors based on normalizing flows or adversarial networks. We find that DDVI improves inference and learning in deep latent variable models across common benchmarks as well as on a motivating task in biology---inferring latent ancestry from human genomes---where it outperforms strong baselines on the Thousand Genomes dataset.

In this paper, we investigate a variant of the classical stochastic Multi-armed Bandit (MAB) problem, where the payoff received by an agent (either cost or reward) is both delayed, and directly corresponds to the magnitude of the delay. This setting models faithfully many real world scenarios such as the time it takes for a data packet to traverse a network given a choice of route (where delay serves as the agent’s cost); or a user's time spent on a web page given a choice of content (where delay serves as the agent’s reward). Our main contributions are tight upper and lower bounds for both the cost and reward settings. For the case that delays serve as costs, which we are the first to consider, we prove optimal regret that scales as ∑i:Δi > 0(log T)/Δi + d*, where T is the maximal number of steps, Δi are the sub-optimality gaps and d* is the minimal expected delay amongst arms. For the case that delays serves as rewards, we show optimal regret of ∑i:Δi > 0(log T)/Δi + d̄, where d̄ is the second maximal expected delay. These improve over the regret in the general delay-dependent payoff setting, which scales as ∑i:Δi > 0(log T)/Δi+ D, where D is the maximum possible delay. Our regret bounds highlight the difference between the cost and reward scenarios, showing that the improvement in the cost scenario is more significant than for the reward. Finally, we accompany our theoretical results with an empirical evaluation.

Deep learning based dehazing networks trained on paired synthetic data have shown impressive performance, but they struggle with significant degradation in generalization ability on real-world hazy scenes. In this paper, we propose Dehaze-RetinexGAN, a lightweight Retinex-based Generative Adversarial Network for real-world image Dehazing using unpaired data. Our Dehaze-RetinexGAN consists of two stages: self-supervised pre-training and weakly-supervised fine-tuning. During the pre-training, we reduce the image dehazing task to an illumination-reflectance decomposition task based on the duality correlation between Retinex and dehazing. Specifically, a decomposition network named DecomNet is constructed to obtain an illumination and a reflectance, simultaneously. Moreover, a self-supervised learning strategy is developed to construct the connection between the preliminary dehazed result and the input hazy image, which constrains the solution space of DecomNet and accelerates training, leading to a more realistic dehazed result. In the fine-tuning stage, we develop a dual DTCWT-based attention module and embed it into the U-Net architecture to further improve the quality of preliminary result in the frequency domain. In addition, the adversarial learning is employed to constrain the relevance between the clean image and the final dehazed result in a weakly supervised manner, which can promote more natural performance. Extensive experiments on several real-world datasets demonstrate that our proposed framework performs favorably over state-of-the-art dehazing methods in visual quality and quantitative evaluation.

Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses. It is challenging to timely prevent such model-stealing attacks to achieve strong protection and maintain utility. In this paper, we propose a novel non-parametric detector called Account-aware Distribution Discrepancy (ADD) to recognize queries from malicious users by leveraging account-wise local dependency. We formulate each class as a Multivariate Normal distribution (MVN) in the feature space and measure the malicious score as the sum of weighted class-wise distribution discrepancy. The ADD detector is combined with random-based prediction poisoning to yield a plug-and-play defense module named D-ADD for image classification models. Results of extensive experimental studies show that D-ADD achieves strong defense against different types of attacks with little interference in serving benign users for both soft and hard-label settings.

Federated learning is susceptible to model poisoning attacks, especially those meticulously crafted for servers. Traditional defense methods mainly focus on updating assessments or robust aggregation against manually crafted myopic attacks. When facing advanced attacks, their defense stability is notably insufficient. Therefore, it is imperative to develop adaptive defenses against such advanced poisoning attacks. We find that benign clients exhibit significantly higher data distribution stability than malicious clients in federated learning in both CV and NLP tasks. Therefore, the malicious clients can be recognized by observing the stability of their data distribution. In this paper, we propose AdaAggRL, an RL-based Adaptive Aggregation method, to defend against sophisticated poisoning attacks. Specifically, we first utilize distribution learning to simulate the clients' data distributions. Then, we use maximum mean discrepancy (MMD) to calculate the pairwise similarity of the current local model data distribution, its historical data distribution, and global model data distribution. Finally, we use policy learning to adaptively determine the aggregation weights based on the above similarities. Experiments on four real-world datasets demonstrate that the proposed defense model significantly outperforms widely adopted defense models for sophisticated attacks.