IJCAI 2024 论文列表

Rapid advancements in neuroimaging techniques, such as magnetic resonance imaging (MRI), have facilitated the acquisition of the structural and functional characteristics of the brain. Brain network analysis is one of the essential tools for exploring brain mechanisms from MRI, providing valuable insights into the brain's organization, and stimulating the understanding of brain cognition and pathology of neurodegenerative diseases. Graph Neural Networks (GNNs) are commonly used for brain network analysis, but they are limited by the scarcity of medical data. Although Graph Contrastive Learning methods have been developed to address this, they often involve graph augmentations that distort the anatomical brain structures. To address these challenges, an augmentation-free contrastive learning method, named Self-Promoted Clustering-based Contrastive Learning(SPCCL), is proposed in this paper. Specifically, by introducing a clustering-based contrastive Learning loss and a self-promoted contrastive pairs creation scheme, the proposed SPCCL can be pre-trained from additional healthy subjects' data that are relatively easier to acquire than disorder ones. The proposed SPCCL leverages these additional data with respect to the integrity of the original brain structure, making it a promising approach for effective brain network analysis. Comprehensive experiments are conducted on an open-access schizophrenic dataset, demonstrating the effectiveness of the proposed method.

Learning effective strategies in sparse reward tasks is one of the fundamental challenges in reinforcement learning. This becomes extremely difficult in multi-agent environments, as the concurrent learning of multiple agents induces the non-stationarity problem and a sharply increased joint state space. Existing works have attempted to promote multi-agent cooperation through experience sharing. However, learning from a large collection of shared experiences is inefficient as there are only a few high-value states in sparse reward tasks, which may instead lead to the curse of dimensionality in large-scale multi-agent systems. This paper focuses on sparse-reward multi-agent cooperative tasks and proposes an effective experience-sharing method, Multi-Agent Selective Learning (MASL), to boost sample-efficient training by reusing valuable experiences from other agents. MASL adopts a retrogression-based selection method to identify high-value traces of agents from the team rewards, based on which some recall traces are generated and shared among agents to motivate effective exploration. Moreover, MASL selectively considers information from other agents to cope with the non-stationarity issue while enabling efficient training for large-scale agents. Experimental results show that MASL significantly improves sample efficiency compared with state-of-the-art MARL algorithms in cooperative tasks with sparse rewards.

We study committee elections from a perspective of finding the most conflicting candidates, that is, candidates that imply the largest amount of conflict, as per voter preferences. By proposing basic axioms to capture this objective, we show that none of the prominent multiwinner voting rules meet them. Consequently, we design committee voting rules compliant with our desiderata, introducing conflictual voting rules. A subsequent deepened analysis sheds more light on how they operate. Our investigation identifies various aspects of conflict, for which we come up with relevant axioms and quantitative measures, which may be of independent interest. We support our theoretical study with experiments on both real-life and synthetic data.

The Moran process is a classic stochastic process that models the rise and takeover of novel traits in network-structured populations. In biological terms, a set of mutants, each with fitness m ∈ (0, ∞) invade a population of residents with fitness 1. Each agent reproduces at a rate proportional to its fitness and each offspring replaces a random network neighbor. The process ends when the mutants either fixate (take over the whole population) or go extinct. The fixation probability measures the success of the invasion. To account for environmental heterogeneity, we study a generalization of the Standard process, called the Heterogeneous Moran process. Here, the fitness of each agent is determined both by its type (resident/mutant) and the node it occupies. We study the natural optimization problem of seed selection: given a budget k, which k agents should initiate the mutant invasion to maximize the fixation probability? We show that the problem is strongly inapproximable: it is NP-hard to distinguish between maximum fixation probability 0 and 1. We then focus on mutant-biased networks, where each node exhibits at least as large mutant fitness as resident fitness. We show that the problem remains NP-hard, but the fixation probability becomes submodular, and thus the optimization problem admits a greedy (1 − 1/e)-approximation. An experimental evaluation of the greedy algorithm along with various heuristics on real-world data sets corroborates our results.

Inspired by the power of Diffusion Models (DM) verified in various fields, some pioneering works have started to explore DM in recommendation. However, these prevailing endeavors commonly implement diffusion on item indices, leading to the increasing time complexity, the lack of transferability, and the inability to fully harness item semantic information. To tackle these challenges, we propose SeeDRec, a sememe-based diffusion framework for sequential recommendation (SR). Specifically, inspired by the notion of sememe in NLP, SeeDRec first defines a similar concept of recommendation sememe to represent the minimal interest unit and upgrades the specific diffusion objective from the item level to the sememe level. With the Sememe-to-Interest Diffusion Model (S2IDM), SeeDRec can accurately capture the user's diffused interest distribution learned from both local interest evolution and global interest generalization while maintaining low computational costs. Subsequently, an Interest-aware Prompt-enhanced (IPE) strategy is proposed to better guide each user's sequential behavior modeling via the learned user interest distribution. Extensive experiments on nine SR datasets and four cross-domain SR datasets verify its effectiveness and universality. The code is available in https://github.com/hulkima/SeeDRec.

Syntax-guided synthesis is commonly used to generate programs encoding policies. In this approach, the set of programs, that can be written in a domain-specific language defines the search space, and an algorithm searches within this space for programs that encode strong policies. In this paper, we propose an alternative method for synthesizing programmatic policies, where we search within an approximation of the language's semantic space. We hypothesized that searching in semantic spaces is more sample-efficient compared to syntax-based spaces. Our rationale is that the search is more efficient if the algorithm evaluates different agent behaviors as it searches through the space, a feature often missing in syntax-based spaces. This is because small changes in the syntax of a program often do not result in different agent behaviors. We define semantic spaces by learning a library of programs that present different agent behaviors. Then, we approximate the semantic space by defining a neighborhood function for local search algorithms, where we replace parts of the current candidate program with programs from the library. We evaluated our hypothesis in a real-time strategy game called MicroRTS. Empirical results support our hypothesis that searching in semantic spaces can be more sample-efficient than searching in syntax-based spaces.

Large Language Models (LLM) can invoke a variety of tools and APIs to complete complex tasks. The computer, as the most powerful and universal tool, could potentially be controlled by a trained LLM agent. Powered by the computer, we can hopefully build a more generalized agent to assist humans in various daily digital works. In this paper, we construct an environment for a Vision Language Model (VLM) agent to interact with a real computer screen. Within this environment, the agent can observe screenshots and manipulate the Graphical User Interface (GUI) by outputting mouse and keyboard actions. We also design an automated control pipeline that includes planning, acting, and reflecting phases, guiding the agent to continuously interact with the environment and complete multi-step tasks. Additionally, we construct the ScreenAgent Dataset, which collects screenshots and action sequences when completing daily computer tasks. Finally, we train a model, ScreenAgent, which achieves comparable computer control capabilities to GPT-4V and demonstrated more precise UI positioning capabilities. Our attempts could inspire further research on building a generalist LLM agent. The code and more detailed information are at https://github.com/niuzaisheng/ScreenAgent.

Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. Our model improves upon the PaLI architecture with the flexible patching strategy of pix2struct and is trained on a unique mixture of datasets. At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements. We use these text annotations to describe screens to Large Language Models and automatically generate question-answering (QA), UI navigation, and summarization training datasets at scale. We run ablation studies to demonstrate the impact of these design choices. At only 5B parameters, ScreenAI achieves new state-of-the-art results on UI- and infographics-based tasks (Multipage DocVQA, WebSRC, and MoTIF), and new best-in-class performance on others (ChartQA, DocVQA, and InfographicVQA) compared to models of similar size. Finally, we release three new datasets: one focused on the screen annotation task and two others focused on question answering.

Multivariant time series (MTS) data are usually incomplete in real scenarios, and imputing the incomplete MTS is practically important to facilitate various time series mining tasks. Recently, diffusion model-based MTS imputation methods have achieved promising results by utilizing CNN or attention mechanisms for temporal features learning. However, it is hard to adaptively trade off the diverse effects of local and global temporal features by simply combining CNN and attention. To address this issue, we propose a Score-weighted Convolutional Diffusion Model (Score-CDM for short), whose backbone consists of a Score-weighted Convolution Module (SCM) and an Adaptive Reception Module (ARM). SCM adopts a score map to capture the global temporal features in the time domain, while ARM uses a Spectral2Time Window Block (S2TWB) to convolve the local time series data in the spectral domain. Benefiting from the time convolution properties of Fast Fourier Transformation, ARM can adaptively change the receptive field of the score map, and thus effectively balance the local and global temporal features. We conduct extensive evaluations on three real MTS datasets of different domains, and the result verifies the effectiveness of the proposed Score-CDM.

Jointly using text and sketch for scene-level image retrieval utilizes the complementary between text and sketch to describe the fine-grained scene content and retrieve the target image, which plays a pivotal role in accurate image retrieval. Existing methods directly fuse the features of sketch and text and thus suffer from the bottleneck of limited utilization for crucial semantic and structural information, leading to inaccurate matching with images. In this paper, we propose SceneDiff, a novel retrieval network that leverages a pre-trained diffusion model to establish a shared generative latent space, enabling a joint latent representation learning for both sketch and text features and precise alignment with the corresponding image. Specifically, we encode text, sketch and image features, and project them into the diffusion-based share space, conditioning the denoising process on sketch and text features to generate latent fusion features, while employing the pre-trained autoencoder for latent image features. Within this space, we introduce the content-aware feature transformation module to reconcile encoded sketch and image features with the diffusion latent space's dimensional requirements and preserve their visual content information. Then we augment the representation capability of the generated latent fusion features by integrating multiple samplings with partition attention, and utilize contrastive learning to align both direct fusion features and generated latent fusion features with corresponding image representations. Our method outperforms the state-of-the-art works through extensive experiments, providing a novel insight into the related retrieval field.

Person search aims to localize specific a target person from a gallery set of images with various scenes. As the scene of moving pedestrian changes, the captured person image inevitably bring in lots of background noise and foreground noise on the person feature, which are completely unrelated to the person identity, leading to severe performance degeneration. To address this issue, we present a Scene-Adaptive Person Search (SEAS) model by introducing bilateral modulations to simultaneously eliminate scene noise and maintain a consistent person representation to adapt to various scenes. In SEAS, a Background Modulation Network (BMN) is designed to encode the feature extracted from the detected bounding box into a multi-granularity embedding, which reduces the input of background noise from multiple levels with norm-aware. Additionally, to mitigate the effect of foreground noise on the person feature, SEAS introduces a Foreground Modulation Network (FMN) to compute the clutter reduction offset for the person embedding based on the feature map of the scene image. By bilateral modulations on both background and foreground within an end-to-end manner, SEAS obtains consistent feature representations without scene noise. SEAS can achieve state-of-the-art (SOTA) performance on two benchmark datasets, CUHK-SYSU with 97.1% mAP and PRW with 60.5% mAP. The code is available at https://github.com/whbdmu/SEAS.

In a regression task, a function is learned from labeled data to predict the labels at new data points. The goal is to achieve small prediction errors. In symbolic regression, the goal is more ambitious, namely, to learn an interpretable function that makes small prediction errors. This additional goal largely rules out the standard approach used in regression, that is, reducing the learning problem to learning parameters of an expansion of basis functions by optimization. Instead, symbolic regression methods search for a good solution in a space of symbolic expressions. To cope with the typically vast search space, most symbolic regression methods make implicit, or sometimes even explicit, assumptions about its structure. Here, we argue that the only obvious structure of the search space is that it contains small expressions, that is, expressions that can be decomposed into a few subexpressions. We show that systematically searching spaces of small expressions finds solutions that are more accurate and more robust against noise than those obtained by state-of-the-art symbolic regression methods. In particular, systematic search outperforms state-of-the-art symbolic regressors in terms of its ability to recover the true underlying symbolic expressions on established benchmark data sets.

Inertial sensors, serving as attitude and motion sensing components, are extensively used in various portable devices spanning consumer electronics, sports health, aerospace, etc. However, the severe intrinsic errors of inertial sensors greatly restrict their capability to implement advanced functions, such as motion tracking and semantic recognition. Although generative models hold significant potential for signal enhancement, unsupervised or weakly-supervised generative methods may not achieve ideal generation results due to the absence of guidance from paired data. To address this, we propose a scale and direction-guided generative adversarial network (SDG-GAN), which provides dual guidance mechanisms for GAN with unpaired data across two practical application scenarios. In the unsupervised scenario where only unpaired signals of varying quality are available, our scale-guided GAN (SG-GAN) forces the generator to learn high-quality signal characteristics at different scales simultaneously via the proposed self-supervised zoom constraint, thereby facilitating multi-scale interactive learning. In the weakly-supervised scenario, where additional experimental equipment can provide some motion information, our direction-guided GAN (DG-GAN) introduces auxiliary tasks to supervise signal generation while avoiding interference from auxiliary tasks on the main generation task. Extensive experiments demonstrate that both the unsupervised SG-GAN and the weakly-supervised DG-GAN significantly outperform all comparison methods, including fully-supervised approaches. The combined SDG-GAN achieves remarkable results, enabling unimaginable tasks based on the original inertial signal, such as 3D motion tracking.

We consider the problem of computing high-quality Euclidean shortest paths amidst obstacles on a large scale. By transferring and adapting speed-up techniques from the road network setting, we are able to compute source target paths for problem instances with several million obstacle vertices within few milliseconds after moderate preprocessing. We show experimentally that for small instances where optimal solutions are easily available on average our computed paths are less than 0.3% longer than the optimum. For large instances a new lower-bounding technique shows that on average our computed paths are less than 2% longer than the optimum paths. We compare our approach with the current state-of-the-art on problem instances derived from the OpenStreetMap project.

Multi-Agent Path Finding (MAPF) involves determining paths for multiple agents to travel simultaneously and collision-free through a shared area toward given goal locations. This problem is computationally complex, especially when dealing with large numbers of agents, as is common in realistic applications like autonomous vehicle coordination. Finding an optimal solution is often computationally infeasible, making the use of approximate, suboptimal algorithms essential. Adding to the complexity, agents might act in a self-interested and strategic way, possibly misrepresenting their goals to the MAPF algorithm if it benefits them. Although the field of mechanism design offers tools to align incentives, using these tools without careful consideration can fail when only having access to approximately optimal outcomes. In this work, we introduce the problem of scalable mechanism design for MAPF and propose three strategyproof mechanisms, two of which even use approximate MAPF algorithms. We test our mechanisms on realistic MAPF domains with problem sizes ranging from dozens to hundreds of agents. We find that they improve welfare beyond a simple baseline.

Hub Labeling and A* are two well-established algorithms for shortest path computation in large graphs. Hub Labeling offers excellent query times for distance computation, but at the cost of a high space consumption for label storage. Landmark-based A* search requires less space but answers queries much slower. Recently, Landmark Hub Labeling (LHL) has been proposed, which combines both concepts and achieves a smaller space consumption than Hub Labeling and also much better query times than A*. However, the known algorithms for computing a LHL do not scale to large graphs, limiting its applicability. In this paper, we devise novel algorithms for LHL construction that work on graphs with millions of edges. We also further improve the LHL query answering algorithm and investigate how to reduce the space consumption of labeling techniques by performing bounded suboptimal pathfinding. In an extensive experimental study, we demonstrate the effectiveness of our methods and illuminate that sensible trade-offs between space consumption, query time, and path quality can be achieved with LHL.

Federated unlearning has emerged as a promising paradigm to erase the client-level data effect without affecting the performance of collaborative learning models. However, the federated unlearning process often introduces extensive storage overhead and consumes substantial computational resources, thus hindering its implementation in practice. To address this issue, this paper proposes a scalable federated unlearning framework based on isolated sharding and coded computing. We first divide distributed clients into multiple isolated shards across stages to reduce the number of clients being affected. Then, to reduce the storage overhead of the central server, we develop a coded computing mechanism by compressing the model parameters across different shards. In addition, we provide the theoretical analysis of time efficiency and storage effectiveness for the isolated and coded sharding. Finally, extensive experiments on two typical learning tasks, i.e., classification and generation, demonstrate that our proposed framework can achieve better performance than three state-of-the-art frameworks in terms of accuracy, retraining time, storage overhead, and F1 scores for resisting membership inference attacks.

Ranked choice voting (RCV) is a voting rule that iteratively eliminates least-popular candidates until there is a single winner with a majority of all remaining votes. In this work, we explore three central questions about predicting the outcome of RCV on an election given a uniform sample of votes. First, in theory, how poorly can RCV sampling predict RCV outcomes? Second, can we use insights from the recently-proposed map of elections to better predict RCV outcomes? Third, is RCV the best rule to use on a sample to predict the outcome of RCV in real-world elections? We find that although RCV can do quite poorly in the worst case and it may be better to use other rules to predict RCV winners on synthetic data from the map of elections, RCV generally predicts itself well on real-world data, further contributing to its appeal as a theoretically-flawed but practicable voting process. We further supplement our work by exploring the effect of margin of victory (MoV) on sampling accuracy.

Federated causal discovery (FCD) aims to uncover causal relationships among variables from decentralized data across multiple clients, while preserving data privacy. In practice, the sample quality of each client's local data may vary across different variable spaces, referred to as sample quality heterogeneity. Thus, data from different clients might be suitable for learning different causal relationships among variables. Model aggregated under existing FCD methods requires the entire model parameters from each client, thereby being unable to handle the sample quality heterogeneity issue. In this paper, we propose the Federated Adaptive Causal Discovery (FedACD) method to bridge this gap. During federated model aggregation, it adaptively selects the causal relationships learned under the "good" variable space (i.e., one with high-quality samples) from each client, while masking those learned under the "bad" variable space (i.e., one with low-quality samples). This way, each client only needs to send the optimal learning results to the server, achieving accurate FCD. Extensive experiments on various types of datasets demonstrate significant advantages of FedACD over existing methods. The source code is available at https://github.com/Xianjie-Guo/FedACD.