AAAI 2025 论文列表

Implicit Neural Representation (INR) has shown great potential in constructing the complex nature signal as a continuous implicit function. However, the representation results are incomplete since different components of the signal correspond to different frequencies and neural network inherently tends to low-frequency convergence. In this paper, we propose the adaptive Wavelet-Positional Encoding (WPE) to precisely represent content under different frequency distributions for coordinate-based implicit representations. The High-Frequency Perception (HFP) method is first proposed to query locations of high-frequency components from input signals, which can be indicated as local centers of WPE. Then, motivated by wavelet series regression, we present to embed these queried low-dimensional coordinate inputs into wavelet-frequency space by WPE to represent fine details of target signals. Experiments demonstrate that the proposed method can be integrated into various INR methods without modifying training frameworks while significantly improving their performance in 1D signal fitting, 2D image regression, and even 3D scene representation.

Unsupervised point cloud shape correspondence aims to establish point-wise correspondences between point clouds without annotated data. Ensuring efficiency and accuracy is crucial for practically implementing point cloud shape correspondence. Although the current methods have achieved desirable performance, the nature of encoding at dense points limits their application in actual scenarios. Moreover, independently computing per-point correspondences results in numerous multiple-to-one erroneous correspondences. To address these issues, we present an Adaptive siamese Masked autoencoder with Global Optimization (AMIGO), comprising a siamese masked autoencoder and a global optimization module. In the siamese masked autoencoder, we downsample the input point cloud and employ adaptive siamese mask operations to boost the coding capabilities of the encoder, thereby mitigating the information loss caused by downsampling. In the global optimization module, optimal transport is only utilized to generate pseudo-labels during the training phase, facilitating the efficient global planning of the correspondence results. Extensive experiments on four standard human and animal benchmarks demonstrate that AMIGO surpasses existing methods with remarkable margins, achieving new state-of-the-art results.

Obtaining high certainty in predictive models is crucial for making informed and trustworthy decisions in many scientific and engineering domains. However, extensive experimentation required for model accuracy can be both costly and time-consuming. This paper presents an adaptive sampling approach designed to reduce epistemic uncertainty in predictive models. Our primary contribution is the development of a metric that estimates potential epistemic uncertainty leveraging prediction interval-generation neural networks. This estimation relies on the distance between the predicted upper and lower bounds and the observed data at the tested positions and their neighboring points. Our second contribution is the proposal of a batch sampling strategy based on Gaussian processes (GPs). A GP is used as a surrogate model of the networks trained at each iteration of the adaptive sampling process. Using this GP, we design an acquisition function that selects a combination of sampling locations to maximize the reduction of epistemic uncertainty across the domain. We test our approach on three unidimensional synthetic problems and a multi-dimensional dataset based on an agricultural field for selecting experimental fertilizer rates. The results demonstrate that our method consistently converges faster to minimum epistemic uncertainty levels compared to Normalizing Flows Ensembles, MC-Dropout, and simple GPs.

Class incremental semantic segmentation (CISS) aims to segment new classes during continual steps while preventing the forgetting of old knowledge. Existing methods alleviate catastrophic forgetting by replaying distributions of previously learned classes using stored prototypes or features. However, they overlook a critical issue: in CISS, the representation of class knowledge is updated continuously through incremental learning, whereas prototype replay methods maintain fixed prototypes. This mismatch between updated representation and fixed prototypes limits the effectiveness of the prototype replay strategy. To address this issue, we propose the Adaptive prototype replay (Adapter) for CISS in this paper. Adapter comprises an adaptive deviation compensation (ADC) strategy and an uncertainty-aware constraint (UAC) loss. Specifically, the ADC strategy dynamically updates the stored prototypes based on the estimated representation shift distance to match the updated representation of old class. The UAC loss reduces prediction uncertainty, aggregating discriminative features to aid in generating compact prototypes. Additionally, we introduce a compensation-based prototype similarity discriminative (CPD) loss to ensure adequate differentiation between similar prototypes, thereby enhancing the efficiency of the adaptive prototype replay strategy. Extensive experiments on Pascal VOC and ADE20K datasets demonstrate that Adapter achieves state-of-the-art results and proves effective across various CISS tasks, particularly in challenging multi-step scenarios.

To address catastrophic forgetting in Continual Relation Extraction (CRE), many current approaches rely on memory buffers to rehearse previously learned knowledge while acquiring new tasks. Recently, prompt-based methods have emerged as potent alternatives to rehearsal-based strategies, demonstrating strong empirical performance. However, upon analyzing existing prompt-based approaches for CRE, we identified several critical limitations, such as inaccurate prompt selection, inadequate mechanisms for mitigating forgetting in shared parameters, and suboptimal handling of cross-task and within-task variances. To overcome these challenges, we draw inspiration from the relationship between prefix tuning and mixture of experts, proposing a novel approach that employs a prompt pool for each task, capturing variations within each task while enhancing cross-task variances. Furthermore, we incorporate a generative model to consolidate prior knowledge within shared parameters, eliminating the need for explicit data storage. Extensive experiments validate the efficacy of our approach, demonstrating superior performance over state-of-the-art prompt-based and rehearsal-free methods in continual relation extraction.

In the era of big data, cross-modal retrieval is increasingly important in research and application. Given the latent complexity and non-intuitive nature of cross-modal relationships, leveraging external knowledge such as large models has become a popular approach to facilitate modality alignment. Existing methods typically address these challenges by fine-tuning model encoders or using a fixed number of prompts. However, these approaches struggle with the significant information asymmetry between image-text pairs and the high distribution diversity of image data. These limitations not only introduce noise during training but also reduce the accuracy and generalization capabilities in cross-modal retrieval tasks. To address the above issues, this paper proposes Adaptive Prompt-Based Semantic Embedding with Inspired Potential of Implicit Knowledge (APSE-IPIK). On one hand, we propose an inspired potential strategy to extract fine-grained and multi-perspective text descriptions from large-scale pre-trained multimodal models, which can be seen as implicit knowledge injection. These descriptions are integrated into the visual-semantic embedding through cross-modal semantic alignment with images, balancing the information asymmetry between modalities and reducing the embedding of inaccurate mapping relationships. On the other hand, we construct an instance-level query-based prompt pool strategy to adaptively extract the most relevant prompts, addressing alignment biases caused by intra-modal (especially image) data diversity and improving alignment accuracy. Extensive experiments are conducted on two widely used datasets, Flickr30k and MSCOCO, which show the effectiveness of the proposed method.

In recent years, deep multimodal learning has seen significant advancements. However, there remains a lack of multimodal fusion methods capable of dynamically adjusting the weighting of information both within and across modalities based on input samples. In the domain of multimodal intent recognition, the text modality often contains the most relevant information for intent detection, while the audio and visual modalities provide comparatively less critical information. There is a significant variation in the density of important information across different modalities and samples. To address this challenge, we propose a Dynamic Attention Allocation Fusion (DAF) method with an adaptive network structure that dynamically allocates attention both within individual modalities and across multiple modalities. This approach enables the model to focus more effectively on the most informative modalities and their respective internal features. Furthermore, we introduce a multi-view contrastive learning framework based on DAF (MVCL-DAF). This framework uses distinct and isolated modules to process information from various modalities, taking inspiration from the way the human brain processes multimodal information. Each modality independently infers intent using its respective module, while DAF integrates the multimodal information to produce a comprehensive global intent prediction. The text modality, functioning as the primary modality due to its rich semantic content, guides the other modules in the multi-view contrastive learning process. Extensive experiments demonstrate that our approach significantly outperforms existing state-of-the-art methods.

Transformer-based and MLP-based methods have emerged as leading approaches in time series forecasting (TSF). However, real-world time series often show different patterns at different scales, and future changes are shaped by the interplay of these overlapping scales, requiring high-capacity models. While Transformer-based methods excel in capturing long-range dependencies, they suffer from high computational complexities and tend to overfit. Conversely, MLP-based methods offer computational efficiency and adeptness in modeling temporal dynamics, but they struggle with capturing temporal patterns with complex scales effectively. Based on the observation of multi-scale entanglement effect in time series, we propose a novel MLP-based Adaptive Multi-Scale Decomposition (AMD) framework for TSF. Our framework decomposes time series into distinct temporal patterns at multiple scales, leveraging the Multi-Scale Decomposable Mixing (MDM) block to dissect and aggregate these patterns. Complemented by the Dual Dependency Interaction (DDI) block and the Adaptive Multi-predictor Synthesis (AMS) block, our approach effectively models both temporal and channel dependencies and utilizes autocorrelation to refine multi-scale data integration. Comprehensive experiments demonstrate our AMD framework not only overcomes the limitations of existing methods but also consistently achieves state-of-the-art performance across various datasets.

Estimating service capabilities for logistics terminal stations is essential for guiding operations adjustments to enhance customer experience. However, existing studies often focus on isolated metrics like on-time delivery or complaint rates, each reflecting a specific aspect of service capabilities. To provide a more comprehensive evaluation, we design AdaService, an Adaptive multi-faceted Service capabilities co-estimation framework. We begin by constructing Multi-faceted Hypergraph to encode stations using multiple performance metrics. We then introduce a Multi-faceted Hypergraph Convolution Network (MHCN) to capture the heterogeneous service capabilities across stations, providing a comprehensive capabilities representation. Finally, we apply an Adaptive Multi-faceted Estimation module that uses multi-task learning to model dynamic interactions among these metrics, enhancing predictive accuracy. Extensive evaluation with real-world data collected from nationwide stations in a leading logistics company in China demonstrates that AdaService significantly outperforms state-of-the-art methods, improving estimation accuracy for on-time delivery, on-time pick-up, and complaint rates by up to 18.98%, 9.30%, and 39.62%.

In the domain of merchant-oriented risk control decisions within e-commerce, balancing the effectiveness of risk management with merchant satisfaction remains a critical challenge. Strict risk control strategies, while effectively mitigating risks, often lead to increased merchant dissatisfaction. Conversely, loose policies could enhance the merchant experience but raise the likelihood of incidents, potentially incurring substantial financial losses. Additionally, determining personalized risk control strategies for different merchants to achieve optimal overall risk management effectiveness is crucial. Given the high uncertainty in the outcomes of different risk control decisions, manual strategy allocation and real-time adjustments are commonly implemented in practice, leading to significant human and resource costs. In this work, we present a novel automated risk control decision framework that utilizes unbiased data-driven decision-making and dynamic optimization to automate the allocation and adjustment of risk control strategies. Our proposed solution adapts to various online business requirements, demonstrating exceptional risk management performance and significantly reducing overall costs. This approach has been extensively deployed and validated in Alibaba's risk control operations, achieving large-scale automated risk control decisions.

A market maker is a specialist who provides liquidity by continuously offering bid and ask quotes for a financial asset. The market maker’s objective is to maximize profit while avoiding the accumulation of a large position in the asset to control inventory risk. To achieve model-free results, online learning has been applied to design market-making strategies that make no assumptions on the dynamics of the limit order book and asset price. However, existing work primarily focuses on profit rather than inventory risk. To address this limitation, this paper develops market-making strategies with inventory constraints within the online learning framework. To manage inventory risk, we propose two classes of market-making strategies with fixed bid-ask spreads that serve as reference strategies. Each reference strategy can ensure that the inventory remains under control, which enables the online learning algorithms designed for each class of reference strategies to satisfy inventory constraints. Different from the standard online learning model where the gain in each period is assumed to lie within a fixed bounded interval, the gain in our model depends on a state variable (i.e., the inventory size). Thus, a key challenge in analyzing the regret bounds is to bound the difference between the gains of any two reference strategies, which becomes significantly more complicated compared with scenarios without inventory constraints. By tackling these difficulties, we show that these algorithms achieve low regrets. Experimental results illustrate the superior performance of our algorithms in inventory risk control.

Knockout tournaments, also known as single-elimination or cup tournaments, are a popular form of sports competitions. In the standard probabilistic setting, for each pairing of players, one of the players wins the game with a certain (a priory known) probability. Due to their competitive nature, tournaments are prone to manipulation. We investigate the computational problem of determining whether, for a given tournament, a coalition has a manipulation strategy that increases the winning probability of a designated player above a given threshold. More precisely, in every round of the tournament, coalition players can strategically decide which games to throw based on the advancement of other players to the current round. We call this setting adaptive constructive coalition manipulation. To the best of our knowledge, while coalition manipulation has been studied in the literature, this is the first work to introduce adaptiveness to this context. We show that the above problem is hard for every complexity class in the polynomial hierarchy. On the algorithmic side, we show that the problem is solvable in polynomial time when the coalition size is a constant. Furthermore, we show that the problem is fixed-parameter tractable when parameterized by the coalition size and the size of a minimum player set that must include at least one player from each non-deterministic game. Lastly, we investigate a generalized setting where the tournament tree can be imbalanced.

This paper presents a comprehensive study on the role of Classifier-Free Guidance (CFG) in text-conditioned diffusion models from the perspective of inference efficiency. In particular, we relax the default choice of applying CFG in all diffusion steps and instead propose to search for more efficient guidance policies. We formulate the discovery of such policies in the framework of differentiable neural architecture search. Our findings suggest that, as denoising progresses, the updates produced by CFG become increasingly aligned with simple conditional steps, which renders CFG's additional neural network evaluation redundant, especially in the second half of the denoising process. Building upon this insight, we propose "Adaptive Guidance" (AG), an efficient variant of CFG that adaptively omits network evaluations when the denoising process displays convergence. Our experiments demonstrate that AG preserves CFG's image quality while reducing computation by 25%. Thus, AG constitutes a plug-and-play alternative to Guidance Distillation, achieving 50% of the speed-ups of the latter, while being training-free and retaining the capacity to handle negative prompts. We conclude by uncovering further redundancies of CFG in the first half of the diffusion process, showing that entire neural network evaluations can be replaced by simple affine transformations of past score estimates.

Recently, Large Language Models (LLMs) with in-context learning have demonstrated remarkable potential in handling neural machine translation. However, existing evidence shows that LLMs are prompt-sensitive and it is sub-optimal to apply the fixed prompt to any input for downstream machine translation tasks. To address this issue, we propose an adaptive few-shot prompting (AFSP) framework to automatically select suitable translation demonstrations for various source input sentences to further elicit the translation capability of an LLM for better machine translation. First, we build a translation demonstration retrieval module based on LLM's embedding to retrieve top-k semantic-similar translation demonstrations from aligned parallel translation corpus. Rather than using other embedding models for semantic demonstration retrieval, we build a hybrid demonstration retrieval module based on the embedding layer of the deployed LLM to build better input representation for retrieving more semantic-related translation demonstrations. Then, to ensure better semantic consistency between source inputs and target outputs, we force the deployed LLM itself to generate multiple output candidates in the target language with the help of translation demonstrations and rerank these candidates. Besides, to better evaluate the effectiveness of our AFSP framework on the latest language and extend the research boundary of neural machine translation, we construct a high-quality diplomatic Chinese-English parallel dataset that consists of 5,528 parallel Chinese-English sentences. Finally, extensive experiments on the proposed diplomatic Chinese-English parallel dataset and the United Nations Parallel Corpus (Chinese-English part) show the effectiveness and superiority of our proposed AFSP.

Artificial Intelligence (AI) and Machine Learning hold immense potential to accelerate scientific discovery and engineering design. A fundamental challenge in these domains involves efficiently exploring a large space of hypotheses using expensive experiments in a resource-efficient manner. My research focuses on developing novel adaptive experimental design methods to address this broad challenge. Specifically, I develop new probabilistic modeling and decision making tools that operate in small data settings. These approaches have yielded substantial improvements in sample-efficiency, particularly for black-box optimization over high-dimensional combinatorial spaces (e.g., sequences and graphs). This cover letter outlines key methods I have developed and their real-world sustainability applications in areas such as nano-porous materials discovery, hardware design, and additive manufacturing. Additionally, I highlight my initiatives to foster collaboration between Science/Engineering and AI communities.

Recently, learning-based Underwater Image Enhancement (UIE) methods have demonstrated promising performance. However, existing learning-based methods still face two challenges. 1) They rarely consider the inconsistent degradation levels in different spatial regions and spectral bands simultaneously. 2) They treat all regions equally, ignoring that the regions with high-frequency details are more difficult to reconstruct. To address these challenges, we propose a novel UIE method based on spatial-spectral dual-domain adaptive learning, termed SS-UIE. Specifically, we first introduce a spatial-wise Multi-scale Cycle Selective Scan (MCSS) module and a Spectral-Wise Self-Attention (SWSA) module, both with linear complexity, and combine them in parallel to form a basic Spatial-Spectral block (SS-block). Benefiting from the global receptive field of MCSS and SWSA, SS-block can effectively model the degradation levels of different spatial regions and spectral bands, thereby enabling degradation level-based dual-domain adaptive UIE. By stacking multiple SS-blocks, we build our SS-UIE network. Additionally, a Frequency-Wise Loss (FWL) is introduced to narrow the frequency-wise discrepancy and reinforce the model's attention on the regions with high-frequency details. Extensive experiments validate that the SS-UIE technique outperforms state-of-the-art UIE methods while requiring cheaper computational and memory costs.

Knowledge distillation (KD) aims to improve the performance of lightweight student networks under the guidance of pre-trained teachers. However, the large capacity gap between teachers and students limits the distillation gains. Previous methods addressing this problem have two weaknesses. First, most of them decrease the performance of pre-trained teachers, hindering students from achieving comparable performance. Second, these methods fail to dynamically adjust the transferred knowledge to be compatible with the representation ability of students, which is less effective in bridging the capacity gap. In this paper, we propose Adaptive Dual Guidance Knowledge Distillation (ADG-KD), which retains the guidance of the pre-trained teacher and uses the teacher's bidirectional optimization route guiding the student to alleviate the capacity gap problem. Specifically, ADG-KD introduces an initialized teacher, which has an identical structure to the pre-trained teacher and is optimized through the bidirectional supervision from both the pre-trained teacher and student. In this way, we construct the teacher's bidirectional optimization route to provide the students with an easy-to-hard and compatible knowledge sequence. ADG-KD trains the students under the proposed dual guidance approaches and automatically determines their importance weights, making the transferred knowledge better compatible with the representation ability of students. Extensive experiments on CIFAR-100, ImageNet, and MS-COCO demonstrate the effectiveness of our method.

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires a separate forward pass through the model for each token generated, which is computationally inefficient and poses challenges for deploying LLMs in latency-sensitive scenarios. The main limitations of current decoding methods stem from their inefficiencies and resource demands. Existing approaches either necessitate fine-tuning smaller models, which is resource-intensive, or relying on fixed retrieval schemes to construct drafts for the next tokens, which lack adaptability and fail to generalize across different models and contexts. To address these issues, we introduce a novel methodology called Adaptix, which accelerates LLM decoding without requiring fine-tuning. Our approach involves an adaptive draft-verification process that evolves over time to improve efficiency. We utilize a tri-gram matrix-based LLM representation to dynamically approximate the output distribution of the LLM, allowing the model to adjust to changing token probabilities during the decoding process. Additionally, we implement a draft construction mechanism that effectively balances exploration and exploitation, ensuring that the drafts generated are both diverse and close to the true output distribution of the LLM. The importance of this design lies in its ability to optimize the draft distribution adaptively, leading to faster and more accurate decoding. Through extensive experiments on various benchmark datasets and LLM architectures, we demonstrate that Adaptix significantly accelerates the decoding process while maintaining high accuracy, making it suitable for deployment in a wide range of practical applications.

Few-Shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes from a limited set of training samples without forgetting knowledge of previously learned classes. Conventional FSCIL methods typically build a robust feature extractor during the base training session with abundant training samples and subsequently freeze this extractor, only fine-tuning the classifier in subsequent incremental phases. However, current strategies primarily focus on preventing catastrophic forgetting, considering only the relationship between novel and base classes, without paying attention to the specific decision spaces of each class. To address this challenge, we propose a plug-and-play Adaptive Decision Boundary Strategy (ADBS), which is compatible with most FSCIL methods. Specifically, we assign a specific decision boundary to each class and adaptively adjust these boundaries during training to optimally refine the decision spaces for the classes in each session. Furthermore, to amplify the distinctiveness between classes, we employ a novel inter-class constraint loss that optimizes the decision boundaries and prototypes for each class. Extensive experiments on three benchmarks, namely CIFAR100, miniImageNet, and CUB200, demonstrate that incorporating our ADBS method with existing FSCIL techniques significantly improves performance, achieving overall state-of-the-art results.