AAAI 2024 论文列表

In recent years, significant progress has been made in the field of protein function prediction with the development of various machine-learning approaches. However, most existing methods formulate the task as a multi-classification problem, i.e. assigning predefined labels to proteins. In this work, we propose a novel approach, Prot2Text, which predicts a protein's function in a free text style, moving beyond the conventional binary or categorical classifications. By combining Graph Neural Networks(GNNs) and Large Language Models(LLMs), in an encoder-decoder framework, our model effectively integrates diverse data types including protein sequence, structure, and textual annotation and description. This multimodal approach allows for a holistic representation of proteins' functions, enabling the generation of detailed and accurate functional descriptions. To evaluate our model, we extracted a multimodal protein dataset from SwissProt, and demonstrate empirically the effectiveness of Prot2Text. These results highlight the transformative impact of multimodal models, specifically the fusion of GNNs and LLMs, empowering researchers with powerful tools for more accurate function prediction of existing as well as first-to-see proteins.

We introduce a novel definition for a small set R of k points being "representative" of a larger set in a metric space. Given a set V (e.g., documents or voters) to represent, and a set C of possible representatives, our criterion requires that for any subset S comprising a theta fraction of V, the average distance of S to their best theta*k points in R should not be more than a factor gamma compared to their average distance to the best theta*k points among all of C. This definition is a strengthening of proportional fairness and core fairness, but - different from those notions - requires that large cohesive clusters be represented proportionally to their size. Since there are instances for which - unless gamma is polynomially large - no solutions exist, we study this notion in a resource augmentation framework, implicitly stating the constraints for a set R of size k as though its size were only k/alpha, for alpha > 1. Furthermore, motivated by the application to elections, we mostly focus on the "ordinal" model, where the algorithm does not learn the actual distances; instead, it learns only for each point v in V and each candidate pairs c, c' which of c, c' is closer to v. Our main result is that the Expanding Approvals Rule (EAR) of Aziz and Lee is (alpha, gamma) representative with gamma <= 1 + 6.71 * (alpha)/(alpha-1). Our results lead to three notable byproducts. First, we show that the EAR achieves constant proportional fairness in the ordinal model, giving the first positive result on metric proportional fairness with ordinal information. Second, we show that for the core fairness objective, the EAR achieves the same asymptotic tradeoff between resource augmentation and approximation as the recent results of Li et al., which used full knowledge of the metric. Finally, our results imply a very simple single-winner voting rule with metric distortion at most 44.

We study the problem of fair sequential decision making given voter preferences. In each round, a decision rule must choose a decision from a set of alternatives where each voter reports which of these alternatives they approve. Instead of going with the most popular choice in each round, we aim for proportional representation, using axioms inspired by the multi-winner voting literature. The axioms require that every group of α% of the voters, if it agrees in every round (i.e., approves a common alternative), then those voters must approve at least α% of the decisions. A stronger version of the axioms requires that every group of α% of the voters that agrees in a β fraction of rounds must approve β⋅α% of the decisions. We show that three attractive voting rules satisfy axioms of this style. One of them (Sequential Phragmén) makes its decisions online, and the other two satisfy strengthened versions of the axioms but make decisions semi-online (Method of Equal Shares) or fully offline (Proportional Approval Voting). We present empirical results for these rules based on synthetic data and U.S. political elections. We also run experiments using the moral machine dataset about ethical dilemmas. We train preference models on user responses from different countries and let the models cast votes. We find that aggregating these votes using our rules leads to a more equal utility distribution across demographics than making decisions using a single global preference model.

Rumor detection on social media has become increasingly important. Most existing graph-based models presume rumor propagation trees (RPTs) have deep structures and learn sequential stance features along branches. However, through statistical analysis on real-world datasets, we find RPTs exhibit wide structures, with most nodes being shallow 1-level replies. To focus learning on intensive substructures, we propose Rumor Adaptive Graph Contrastive Learning (RAGCL) method with adaptive view augmentation guided by node centralities. We summarize three principles for RPT augmentation: 1) exempt root nodes, 2) retain deep reply nodes, 3) preserve lower-level nodes in deep sections. We employ node dropping, attribute masking and edge dropping with probabilities from centrality-based importance scores to generate views. A graph contrastive objective then learns robust rumor representations. Extensive experiments on four benchmark datasets demonstrate RAGCL outperforms state-of-the-art methods. Our work reveals the wide-structure nature of RPTs and contributes an effective graph contrastive learning approach tailored for rumor detection through principled adaptive augmentation. The proposed principles and augmentation techniques can potentially benefit other applications involving tree-structured graphs.

Never having seen an object and heard its sound simultaneously, can the model still accurately localize its visual position from the input audio? In this work, we concentrate on the Audio-Visual Localization and Segmentation tasks but under the demanding zero-shot and few-shot scenarios. To achieve this goal, different from existing approaches that mostly employ the encoder-fusion-decoder paradigm to decode localization information from the fused audio-visual feature, we introduce the encoder-prompt-decoder paradigm, aiming to better fit the data scarcity and varying data distribution dilemmas with the help of abundant knowledge from pre-trained models. Specifically, we first propose to construct a Semantic-aware Audio Prompt (SAP) to help the visual foundation model focus on sounding objects, meanwhile, the semantic gap between the visual and audio modalities is also encouraged to shrink. Then, we develop a Correlation Adapter (ColA) to keep minimal training efforts as well as maintain adequate knowledge of the visual foundation model. By equipping with these means, extensive experiments demonstrate that this new paradigm outperforms other fusion-based methods in both the unseen class and cross-dataset settings. We hope that our work can further promote the generalization study of Audio-Visual Localization and Segmentation in practical application scenarios. Project page: https://github.com/GeWu-Lab/Generalizable-Audio-Visual-Segmentation

Multi-modal image segmentation is one of the core issues in computer vision. The main challenge lies in integrating common information between modalities while retaining specific patterns for each modality. Existing methods typically perform full fine-tuning on RGB-based pre-trained parameters to inherit the powerful representation of the foundation model. Although effective, such paradigm is not optimal due to weak transferability and scarce downstream data. Inspired by the recent success of prompt learning in language models, we propose the Grouping Prompt Tuning Framework (GoPT), which introduces explicit semantic grouping to learn modal-related prompts, adapting the frozen pre-trained foundation model to various downstream multi-modal segmentation tasks. Specifically, a class-aware uni-modal prompter is designed to balance intra- and inter-modal semantic propagation by grouping modality-specific class tokens, thereby improving the adaptability of spatial information. Furthermore, an alignment-induced cross-modal prompter is introduced to aggregate class-aware representations and share prompt parameters among different modalities to assist in modeling common statistics. Extensive experiments show the superiority of our GoPT, which achieves SOTA performance on various downstream multi-modal image segmentation tasks by training only < 1% model parameters.

Automatic medical report generation (MRG) is of great research value as it has the potential to relieve radiologists from the heavy burden of report writing. Despite recent advancements, accurate MRG remains challenging due to the need for precise clinical understanding and disease identification. Moreover, the imbalanced distribution of diseases makes the challenge even more pronounced, as rare diseases are underrepresented in training data, making their diagnosis unreliable. To address these challenges, we propose diagnosis-driven prompts for medical report generation (PromptMRG), a novel framework that aims to improve the diagnostic accuracy of MRG with the guidance of diagnosis-aware prompts. Specifically, PromptMRG is based on encoder-decoder architecture with an extra disease classification branch. When generating reports, the diagnostic results from the classification branch are converted into token prompts to explicitly guide the generation process. To further improve the diagnostic accuracy, we design cross-modal feature enhancement, which retrieves similar reports from the database to assist the diagnosis of a query image by leveraging the knowledge from a pre-trained CLIP. Moreover, the disease imbalanced issue is addressed by applying an adaptive logit-adjusted loss to the classification branch based on the individual learning status of each disease, which overcomes the barrier of text decoder's inability to manipulate disease distributions. Experiments on two MRG benchmarks show the effectiveness of the proposed method, where it obtains state-of-the-art clinical efficacy performance on both datasets.

Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (UDA) problem is still not well explored. Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA. However, a major challenge for directly deploying such models on downstream UDA tasks is prompt engineering, which requires aligning the domain knowledge of source and target domains, since the performance of UDA is severely influenced by a good domain-invariant representation. We further propose a Prompt-based Distribution Alignment (PDA) method to incorporate the domain knowledge into prompt learning. Specifically, PDA employs a two-branch prompt-tuning paradigm, namely base branch and alignment branch. The base branch focuses on integrating class-related representation into prompts, ensuring discrimination among different classes. To further minimize domain discrepancy, for the alignment branch, we construct feature banks for both the source and target domains and propose image-guided feature tuning (IFT) to make the input attend to feature banks, which effectively integrates self-enhanced and cross-domain features into the model. In this way, these two branches can be mutually promoted to enhance the adaptation of VLMs for UDA. We conduct extensive experiments on three benchmarks to demonstrate that our proposed PDA achieves state-of-the-art performance. The code is available at https://github.com/BaiShuanghao/Prompt-based-Distribution-Alignment.

Numerous solutions are proposed for the Traffic Signal Control (TSC) tasks aiming to provide efficient transportation and alleviate traffic congestion. Recently, promising results have been attained by Reinforcement Learning (RL) methods through trial and error in simulators, bringing confidence in solving cities' congestion problems. However, performance gaps still exist when simulator-trained policies are deployed to the real world. This issue is mainly introduced by the system dynamic difference between the training simulators and the real-world environments. In this work, we leverage the knowledge of Large Language Models (LLMs) to understand and profile the system dynamics by a prompt-based grounded action transformation to bridge the performance gap. Specifically, this paper exploits the pre-trained LLM's inference ability to understand how traffic dynamics change with weather conditions, traffic states, and road types. Being aware of the changes, the policies' action is taken and grounded based on realistic dynamics, thus helping the agent learn a more realistic policy. We conduct experiments on four different scenarios to show the effectiveness of the proposed PromptGAT's ability to mitigate the performance gap of reinforcement learning from simulation to reality (sim-to-real).

Building teams and promoting collaboration are two very common business activities. An example of these are seen in the TeamingForFunding problem, where research institutions and researchers are interested to identify collaborative opportunities when applying to funding agencies in response to latter's calls for proposals. We describe a novel deployed system to recommend teams using a variety of AI methods, such that (1) each team achieves the highest possible skill coverage that is demanded by the opportunity, and (2) the workload of distributing the opportunities is balanced amongst the candidate members. We address these questions by extracting skills latent in open data of proposal calls (demand) and researcher profiles (supply), normalizing them using taxonomies, and creating efficient algorithms that match demand to supply. We create teams to maximize goodness along a novel metric balancing short- and long-term objectives. We validate the success of our algorithms (1) quantitatively, by evaluating the recommended teams using a goodness score and find that more informed methods lead to recommendations of smaller number of teams but higher goodness, and (2) qualitatively, by conducting a large-scale user study at a college-wide level, and demonstrate that users overall found the tool very useful and relevant. Lastly, we evaluate our system in two diverse settings in US and India (of researchers and proposal calls) to establish generality of our approach, and deploy it at a major US university for routine use.

The aftermath of the Covid-19 pandemic saw more severe outcomes for racial minority groups and economically-deprived communities. Such disparities can be explained by several factors, including unequal access to healthcare, as well as the inability of low income groups to reduce their mobility due to work or social obligations. Moreover, senior citizens were found to be more susceptible to severe symptoms, largely due to age-related health reasons. Adapting vaccine distribution strategies to consider a range of demographics is therefore essential to address these disparities. In this study, we propose a novel approach that utilizes influence maximization (IM) on mobility networks to develop vaccination strategies which incorporate demographic fairness. By considering factors such as race, social status, age, and associated risk factors, we aim to optimize vaccine distribution to achieve various fairness definitions for one or more protected attributes at a time. Through extensive experiments conducted on Covid-19 spread in three major metropolitan areas across the United States, we demonstrate the effectiveness of our proposed approach in reducing disease transmission and promoting fairness in vaccination distribution.

Counterfactual explanations shed light on the decisions of black-box models by explaining how an input can be altered to obtain a favourable decision from the model (e.g., when a loan application has been rejected). However, as noted recently, counterfactual explainers may lack robustness in the sense that a minor change in the input can cause a major change in the explanation. This can cause confusion on the user side and open the door for adversarial attacks. In this paper, we study some sources of non-robustness. While there are fundamental reasons for why an explainer that returns a single counterfactual cannot be robust in all instances, we show that some interesting robustness guarantees can be given by reporting multiple rather than a single counterfactual. Unfortunately, the number of counterfactuals that need to be reported for the theoretical guarantees to hold can be prohibitively large. We therefore propose an approximation algorithm that uses a diversity criterion to select a feasible number of most relevant explanations and study its robustness empirically. Our experiments indicate that our method improves the state-of-the-art in generating robust explanations, while maintaining other desirable properties and providing competitive computational performance.

We study the budget aggregation problem in which a set of strategic voters must split a finite divisible resource (such as money or time) among a set of competing projects. Our goal is twofold: We seek truthful mechanisms that provide fairness guarantees to the projects. For the first objective, we focus on the class of moving phantom mechanisms, which are -- to this day -- essentially the only known truthful mechanisms in this setting. For project fairness, we consider the mean division as a fair baseline, and bound the maximum difference between the funding received by any project and this baseline. We propose a novel and simple moving phantom mechanism that provides optimal project fairness guarantees. As a corollary of our results, we show that our new mechanism minimizes the L1 distance to the mean for three projects and gives the first non-trivial bounds on this quantity for more than three projects.

Knowledge distillation aims at transferring knowledge from the teacher model to the student one by aligning their distributions. Feature-level distillation often uses L2 distance or its variants as the loss function, based on the assumption that outputs follow normal distributions. This poses a significant challenge when distribution gaps are substantial since this loss function ignores the variance term. To address the problem, we propose to decompose the transfer objective into small parts and optimize it progressively. This process is inspired by diffusion models from which the noise distribution is mapped to the target distribution step by step. However, directly employing diffusion models is impractical in the distillation scenario due to its heavy reverse process. To overcome this challenge, we adopt the structural re-parameterization technique to generate multiple student features to approximate the teacher features sequentially. The multiple student features are combined linearly in inference time without extra cost. We present extensive experiments performed on various transfer scenarios, such as CNN-to-CNN and Transformer-to-CNN, that validate the effectiveness of our approach.

In spite of the rapidly evolving landscape of text-to-image generation, the synthesis and manipulation of multiple entities while adhering to specific relational constraints pose enduring challenges. This paper introduces an innovative progressive synthesis and editing operation that systematically incorporates entities into the target image, ensuring their adherence to spatial and relational constraints at each sequential step. Our key insight stems from the observation that while a pre-trained text-to-image diffusion model adeptly handles one or two entities, it often falters when dealing with a greater number. To address this limitation, we propose harnessing the capabilities of a Large Language Model (LLM) to decompose intricate and protracted text descriptions into coherent directives adhering to stringent formats. To facilitate the execution of directives involving distinct semantic operations—namely insertion, editing, and erasing—we formulate the Stimulus, Response, and Fusion (SRF) framework. Within this framework, latent regions are gently stimulated in alignment with each operation, followed by the fusion of the responsive latent components to achieve cohesive entity manipulation. Our proposed framework yields notable advancements in object synthesis, particularly when confronted with intricate and lengthy textual inputs. Consequently, it establishes a new benchmark for text-to-image generation tasks, further elevating the field's performance standards.

Deep Neural Networks (DNN) are susceptible to backdoor attacks where malicious attackers manipulate the model's predictions via data poisoning. It is hence imperative to develop a strategy for training a clean model using a potentially poisoned dataset. Previous training-time defense mechanisms typically employ an one-time isolation process, often leading to suboptimal isolation outcomes. In this study, we present a novel and efficacious defense method, termed Progressive Isolation of Poisoned Data (PIPD), that progressively isolates poisoned data to enhance the isolation accuracy and mitigate the risk of benign samples being misclassified as poisoned ones. Once the poisoned portion of the dataset has been identified, we introduce a selective training process to train a clean model. Through the implementation of these techniques, we ensure that the trained model manifests a significantly diminished attack success rate against the poisoned data. Extensive experiments on multiple benchmark datasets and DNN models, assessed against nine state-of-the-art backdoor attacks, demonstrate the superior performance of our PIPD method for backdoor defense. For instance, our PIPD achieves an average True Positive Rate (TPR) of 99.95% and an average False Positive Rate (FPR) of 0.06% for diverse attacks over CIFAR-10 dataset, markedly surpassing the performance of state-of-the-art methods. The code is available at https://github.com/RorschachChen/PIPD.git.

Painterly image harmonization aims to harmonize a photographic foreground object on the painterly background. Different from previous auto-encoder based harmonization networks, we develop a progressive multi-stage harmonization network, which harmonizes the composite foreground from low-level styles (e.g., color, simple texture) to high-level styles (e.g., complex texture). Our network has better interpretability and harmonization performance. Moreover, we design an early-exit strategy to automatically decide the proper stage to exit, which can skip the unnecessary and even harmful late stages. Extensive experiments on the benchmark dataset demonstrate the effectiveness of our progressive harmonization network.

Pan-sharpening aims to leverage the high-frequency signal of the panchromatic (PAN) image to enhance the resolution of its corresponding multi-spectral (MS) image. However, deep neural networks (DNNs) tend to prioritize learning the low-frequency components during the training process, which limits the restoration of high-frequency edge details in MS images. To overcome this limitation, we treat pan-sharpening as a coarse-to-fine high-frequency restoration problem and propose a novel method for achieving high-quality restoration of edge information in MS images. Specifically, to effectively obtain fine-grained multi-scale contextual features, we design a Band-limited Multi-scale High-frequency Generator (BMHG) that generates high-frequency signals from the PAN image within different bandwidths. During training, higher-frequency signals are progressively injected into the MS image, and corresponding residual blocks are introduced into the network simultaneously. This design enables gradients to flow from later to earlier blocks smoothly, encouraging intermediate blocks to concentrate on missing details. Furthermore, to address the issue of pixel position misalignment arising from multi-scale features fusion, we propose a Spatial-spectral Implicit Image Function (SIIF) that employs implicit neural representation to effectively represent and fuse spatial and spectral features in the continuous domain. Extensive experiments on different datasets demonstrate that our method outperforms existing approaches in terms of quantitative and visual measurements for high-frequency detail recovery.

Compared to conventional semantic segmentation with pixel-level supervision, weakly supervised semantic segmentation (WSSS) with image-level labels poses the challenge that it commonly focuses on the most discriminative regions, resulting in a disparity between weakly and fully supervision scenarios. A typical manifestation is the diminished precision on object boundaries, leading to deteriorated accuracy of WSSS. To alleviate this issue, we propose to adaptively partition the image content into certain regions (e.g., confident foreground and background) and uncertain regions (e.g., object boundaries and misclassified categories) for separate processing. For uncertain cues, we propose an adaptive masking strategy and seek to recover the local information with self-distilled knowledge. We further assume that confident regions should be robust enough to preserve the global semantics, and introduce a complementary self-distillation method that constrains semantic consistency between confident regions and an augmented view with the same class labels. Extensive experiments conducted on PASCAL VOC 2012 and MS COCO 2014 demonstrate that our proposed single-stage approach for WSSS not only outperforms state-of-the-art counterparts but also surpasses multi-stage methods that trade complexity for accuracy.