AAAI 2025 论文列表

Finding high-quality representations of heterogeneous tabular datasets is crucial for their effective use in downstream machine learning tasks. Contrastive representation learning (CRL) methods have been previously shown to provide a straightforward way to learn such representations across various data domains. Current tabular CRL methods learn joint embeddings of data instances (tabular rows) by minimizing a contrastive loss between the original instance and its perturbations. Unlike existing tabular CRL methods, we propose leveraging frameworks established in multimodal representation learning, treating each tabular column as a distinct modality. A naive approach that applies a contrastive loss pairwise to tabular columns is not only prohibitively expensive as the number of columns increases, but as we demonstrate, it also fails to capture interactions between variables. Instead, we propose a novel method called ICE-T that learns each columnar embedding by contrasting it with aggregate embeddings of the complementary part of the table, thus capturing interactions and scaling linearly with the number of columns. Unlike existing tabular CRL methods, ICE-T allows for column-specific embeddings to be obtained independently of the rest of the table, enabling the inference of missing values and translation between columnar variables. We provide a comprehensive evaluation of ICE-T across diverse datasets, demonstrating that it generally surpasses the performance of the state-of-the-art alternatives.

Split learning, as a distributed learning framework, effectively addresses the issue of limited computing resources. However, despite achieving a separation of data and computation, recent studies have pointed out that this framework still faces two major security challenges: privacy leakage and model security. Most current research focuses on the problem of privacy leakage, emphasizing how to prevent malicious servers from recovering or inferring the client's private data. However, the issue of model security in split learning has not received sufficient attention. This paper reveals the vulnerability of split learning to backdoor attacks. Since split learning cannot access client data directly, it can only guide the client model to incorporate backdoors through gradients. To address this issue, we design an attack framework that modifies intermediate activations to influence the gradients. We designed a parrot model that learns the client’s feature space, enabling the server to obtain the intermediate activations of poisoned data. During the forward pass, some of the intermediate activations and labels transmitted from the client to the server are replaced with poisoned activations and target labels. This replacement method effectively integrates the backdoor task into the model while partially retaining the main task. This approach ensures that the main task is preserved while seamlessly embedding the backdoor task. Our attack framework minimizes reliance on client knowledge and ensures that the attack process remains undetectable by the client. Through extensive experiments, we demonstrated high attack success rates using triggers such as BadNet, SIG, Blended, and WaNet, while minimizing the impact on the main task.

In the field of multimodal large language models (MLLMs), common methods typically involve unfreezing the language model during training to foster profound visual understanding. However, the fine-tuning of such models with vision-language data often leads to a diminution of their natural language processing (NLP) capabilities. To avoid this performance degradation, a straightforward solution is to freeze the language model while developing multimodal competencies. Unfortunately, previous works have not attained satisfactory outcomes. Building on the strategy of freezing the language model, we conduct thorough structural exploration and introduce the Inner-Adaptor Architecture (IAA). Specifically, the architecture incorporates multiple multimodal adaptors at varying depths within the large language model to facilitate direct interaction with the inherently text-oriented transformer layers, thereby enabling the frozen language model to acquire multimodal capabilities. Unlike previous approaches of freezing language models that require large-scale aligned data, our proposed architecture is able to achieve superior performance on small-scale datasets. We conduct extensive experiments to improve the general multimodal capabilities and visual grounding abilities of the MLLM. Our approach remarkably outperforms previous state-of-the-art methods across various vision-language benchmarks without sacrificing performance on NLP tasks. Code and models will be released.

We study the problem of robust influence maximization in dynamic diffusion networks. In line with recent works, we consider the scenario where the network can undergo insertion and removal of nodes and edges, in discrete time steps, and the influence weights are determined by the features of the corresponding nodes and a global hyperparameter. Given this, our goal is to find, at every time step, the seed set maximizing the worst-case influence spread across all possible values of the hyperparameter. We propose an approximate solution using multiplicative weight updates and a greedy algorithm, with theoretical quality guarantees. Our experiments validate the effectiveness and efficiency of the proposed methods.

The main goal of Few-Shot learning algorithms is to enable learning from small amounts of data. One of the most popular and elegant Few-Shot learning approaches is Model-Agnostic Meta-Learning (MAML). In this paper, we propose a novel framework for Bayesian MAML called BH-MAML, which employs Hypernetworks for weight updates. It learns the universal weights point-wise, but a probabilistic structure is added when adapted for specific tasks. In such a framework, we can use simple Gaussian distributions or more complicated posteriors induced by Continuous Normalizing Flows.

Unsupervised graph alignment aims to find corresponding nodes across different graphs without supervision. Existing methods usually leverage the graph structure to aggregate features of nodes to find relations between nodes. However, the graph structure is inherently limited in pairwise relations between nodes without considering higher-order dependencies among multiple nodes. In this paper, we take advantage of the hypergraph structure to characterize higher-order structural information among nodes for better graph alignment. Specifically, we propose an optimal transport model to learn a hypergraph to capture complex relations among nodes, so that the nodes involved in one hyperedge can be adaptively based on local geometric information. In addition, inspired by the Dirichlet energy function of a hypergraph, we further refine our model to enhance the consistency between structural and feature information in each hyperedge. After that, we jointly leverage graphs and hypergraphs to extract structural and feature information to better model the relations between nodes, which is used to find node correspondences across graphs. We conduct experiments on several benchmark datasets with different settings, and the results demonstrate the effectiveness of our proposed method.

Recent studies have shown that Hypergraph Neural Networks (HGNNs) are vulnerable to adversarial attacks. Existing approaches focus on hypergraph modification attacks guided by gradients, overlooking node spanning in the hypergraph and the group identity of hyperedges, thereby resulting in limited attack performance and detectable attacks. In this manuscript, we present a novel framework, i.e., Hypergraph Attacks via Injecting Homogeneous Nodes into Elite Hyperedges (IE-Attack), to tackle these challenges. Initially, utilizing the node spanning in the hypergraph, we propose the elite hyperedges sampler to identify hyperedges to be injected. Subsequently, a node generator utilizing Kernel Density Estimation (KDE) is proposed to generate the homogeneous node with the group identity of hyperedges. Finally, by injecting the homogeneous node into elite hyperedges, IE-Attack improves the attack performance and enhances the imperceptibility of attacks. Extensive experiments are conducted on five authentic datasets to validate the effectiveness of IE-Attack and the corresponding superiority to state-of-the-art methods.

Reconstructing desired objects and scenes has long been a primary goal in 3D computer vision. Single-view point cloud reconstruction has become a popular technique due to its low cost and accurate results. However, single-view reconstruction methods often rely on expensive CAD models and complex geometric priors. Effectively utilizing prior knowledge about the data remains a challenge. In this paper, we introduce hyperbolic space to 3D point cloud reconstruction, enabling the model to represent and understand complex hierarchical structures in point clouds with low distortion. We build upon previous methods by proposing a hyperbolic Chamfer distance and a regularized triplet loss to enhance the relationship between partial and complete point clouds. Additionally, we design adaptive boundary conditions to improve the model's understanding and reconstruction of 3D structures. Our model outperforms most existing models, and ablation studies demonstrate the significance of our model and its components. Experimental results show that our method significantly improves feature extraction capabilities. Our model achieves outstanding performance in 3D reconstruction tasks.

Long-term Multivariate Time Series (LMTS) forecasting aims to predict extended future trends based on channel-interrelated historical data. Considering the elusive channel correlations, most existing methods compromise by treating channels as independent or tentatively modeling pairwise channel interactions, making it challenging to handle the characteristics of both higher-order interactions and time variation in channel correlations. In this paper, we propose HyperMixer, a novel specializable hypergraph channel mixing plugin which introduces versatile hypergraph structures to capture group channel interactions and time-varying patterns for long-term multivariate time series forecasting. Specifically, to encode the higher-order channel interactions, we structure multiple channels into a hypergraph, achieving a two-phase message-passing mechanism: channel-to-group and group-to-channel. Moreover, the functionally specializable hypergraph structures are presented to boost the capability of hypergraph to capture the time-varying patterns across periods, further refining modeling of channel correlations. Extensive experimental results on seven available benchmark datasets demonstrate the effectiveness and generalization of our plugin in LMTS forecasting. The visual analysis further illustrates that HyperMixer with specializable hypergraphs tailors channel interactions specific to certain periods.

Graph neural networks for hyperbolic space has emerged as a powerful tool for embedding datasets exhibiting a highly non-Euclidean latent anatomy e.g., graphs with hierarchical structures. While several Hyperbolic Graph Neural Networks (Hy-GNNs) have been developed to enhance the representation of hierarchical datasets, they remain susceptible to noise and adversarial attacks, posing serious risks in critical applications. The absence of robust Hy-GNN frameworks underscores a pressing problem. This research addresses this challenge by introducing HyperDefender—a robust and flexible approach designed to fortify Hy-GNNs against adversarial attacks and noises. HyperDefender aims to secure the reliability of applications that depend on the integrity of hierarchical graph-structured data in real-world scenarios. Experimental results demonstrate that HyperDefender significantly improves node classification accuracy across various attacks, effectively mitigating the performance degradation typically observed in Hy-GNNs when the hierarchy in original datasets is compromised.

My thesis primarily focuses on hyper-spectral image generation from frequency spectrums for downstream computer vision tasks. Hyper-spectral images are images with more than three channels commonly created by special hyper-spectral cameras or from frequency spectrums of various sensing applications such as radargrams or distributed acoustic sensing (DAS) systems. The range of frequencies considered in a frequency spectrum is typically too large to map one frequency to one image channel, i.e. we generally consider a frequency spectrum of 2500 Hz. Frequencies need to be binned together in frequency bands where each band forms one image channel. Usually, frequency bands are created either by expert knowledge or trial-and-error. I research how filters can be trained to automatically select frequencies and bin them into frequency bands. My aim is to represent a variety of signal information and decrease noise. Signal representation is optimised for object detection on time-sequenced images with a set number of image channels. The object detection task consists of localising and classifying events in the generated hyper-spectral images. Events are typically types of intrusions, structural changes, or defined actions and structures, e.g. someone climbing a fence. Events and noise often share at least some frequencies and vary between application types.

Scene-level point cloud registration is very challenging when considering dynamic foregrounds. Existing indoor datasets mostly assume rigid motions, so the trained models cannot robustly handle scenes with non-rigid motions. On the other hand, non-rigid datasets are mainly object-level, so the trained models cannot generalize well to complex scenes. This paper presents HybridReg, a new approach to 3D point cloud registration, learning uncertainty mask to account for hybrid motions: rigid for backgrounds and non-rigid/rigid for instance-level foregrounds. First, we build a scene-level 3D registration dataset, namely HybridMatch, designed specifically with strategies to arrange diverse deforming foregrounds in a controllable manner. Second, we account for different motion types and formulate a mask-learning module to alleviate the interference of deforming outliers. Third, we exploit a simple yet effective negative log-likelihood loss to adopt uncertainty to guide the feature extraction and correlation computation. To our best knowledge, HybridReg is the first work that exploits hybrid motions for robust point cloud registration. Extensive experiments show HybridReg's strengths, leading it to achieve state-of-the-art performance on both widely-used indoor and outdoor datasets.

Recent advancements have underscored the exceptional analytical and situational understanding capabilities of Large Language Models (LLMs) in autonomous driving decisions. However, the inherent hallucination issues of LLMs pose significant safety concerns when utilized as standalone decision-making systems. To address these challenges, we propose the Hybrid-Driving framework, which leverages LLMs' situational comprehension and reasoning abilities alongside the specialized driving expertise embedded in knowledge graphs and driving rules, thereby enhancing the safety, robustness, and reliability of autonomous driving decisions. To articulate driving experiences clearly, we introduce the Scenario Evolution Knowledge Graph (SEKG), which integrates scenario prediction and action risk analysis in autonomous driving. By delineating observation areas and defining Time-to-Collision (TTC) levels, we effectively control the number of driving scenario nodes and ensure scenario diversity. Based on the scenario evolution relationships within the SEKG, we predict scenarios and assess associated action risks. Additionally, we implement a rule-filtering mechanism to eliminate unreasonable actions and employ prompt engineering to integrate scenario information, optional actions, and SEKG-based action risk analysis into the LLMs for decision-making. Extensive experiments demonstrate that our approach substantially improves decision success rates compared to using LLMs alone (≥37.5%), as well as surpasses the DiLu framework with LLMs and few-shot driving memory (≥7.5%), and other reinforcement learning methods (≥11%). These results validate the effectiveness of the Hybrid-Driving framework in enhancing LLM reliability for autonomous driving and advocate for its broader application of domain-specific knowledge across other fields.

We study reasoning about relative position, orientation and distance of moving objects in 2D space. We first construct a new hybrid calculus HOPA by augmenting qualitative distance and quantitative constraints into Oriented Point Relation Algebra (OPRA). Then we develop a framework for consistency checking and reasoning with HOPA using Answer Set Programming. This framework can also explain the source of inconsistency, infer new knowledge and generate a layout of objects and their orientation in the discrete space. The framework is capable of reasoning with (un)certain, heterogenous and presumed information. We evaluate efficiency and scalability of our method by computational experiments, and illustrate its applications with sample scenarios from robotic perception and marine navigation.

This paper proposes a novel quantum style transfer (QST) in hybrid quantum-classical computing. QST leverages quantum computing's ability to process high-dimensional data efficiently. Our approach aims to decrease both inference time and complexity while maintaining performance, presenting a viable solution that enhances the scalability and efficiency of image generation technologies.

Biophysical models offer valuable insights into climate-phenology relationships in both natural and agricultural settings. However, there are substantial structural discrepancies across models which require site-specific recalibration, often yielding inconsistent predictions under similar climate scenarios. Machine learning methods offer data-driven solutions, but often lack interpretability and alignment with existing knowledge. We present a phenology model describing dormancy in fruit trees, integrating conventional biophysical models with a neural network to address their structural disparities. We evaluate our hybrid model in an extensive case study predicting cherry tree phenology in Japan, South Korea and Switzerland. Our approach consistently outperforms both traditional biophysical and machine learning models in predicting blooming dates across years. Additionally, the neural network's adaptability facilitates parameter learning for specific tree varieties, enabling robust generalization to new sites without site-specific recalibration. This hybrid model leverages both biophysical constraints and data-driven flexibility, offering a promising avenue for accurate and interpretable phenology modeling.

Distributed optimization is the standard way of speeding up machine learning training, and most of the research in the area focuses on distributed first-order, gradient-based methods. Yet, there are settings where some computationally-bounded nodes may not be able to implement first-order, gradient-based optimization, while they could still contribute to joint optimization tasks. In this paper, we initiate the study of hybrid decentralized optimization, studying settings where nodes with zeroth-order and first-order optimization capabilities co-exist in a distributed system, and attempt to jointly solve an optimization task over some data distribution. We essentially show that, under reasonable parameter settings, such a system can not only withstand noisier zeroth-order agents but can even benefit from integrating such agents into the optimization process, rather than ignoring their information. At the core of our approach is a new analysis of distributed optimization with noisy and possibly-biased gradient estimators, which may be of independent interest. Our results hold for both convex and non-convex objectives. Experimental results on standard optimization tasks confirm our analysis, showing that hybrid first-zeroth order optimization can be practical, even when training deep neural networks.

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods.

Human-in-the-loop (HIL) systems have emerged as a promising approach for combining the strengths of data-driven machine learning models with the contextual understanding of human experts. However, a deeper look into several of these systems reveals that calling them HIL would be a misnomer, as they are quite the opposite, namely AI-in-the-loop (AI2L) systems: the human is in control of the system, while the AI is there to support the human. We argue that existing evaluation methods often overemphasize the machine (learning) component's performance, neglecting the human expert's critical role. Consequently, we propose an AI2L perspective, which recognizes that the human expert is an active participant in the system, significantly influencing its overall performance. By adopting an AI2L approach, we can develop more comprehensive systems that faithfully model the intricate interplay between the human and machine components, leading to more effective and robust AI systems.