IJCAI 2024 论文列表

This paper presents three Mahjong AI competitions we held at IJCAI. We briefly introduce the rule of Mahjong and its challenges to AI algorithms. By showing the results and the application of various algorithms in the competitions, we claim that existing algorithms show promising results in Mahjong, while open problems remain and more efforts are needed towards solving this complex game.

Machine unlearning aims to remove specific knowledge from a well-trained machine learning model. This topic has gained significant attention recently due to the widespread adoption of machine learning models across various applications and the accompanying privacy, legal, and ethical considerations. During the unlearning process, models are typically presented with data that specifies which information should be erased and which should be retained. Nonetheless, practical challenges arise due to prevalent issues of data quality issues and access restrictions. This paper explores these challenges and introduces strategies to address problems related to unsupervised data, weakly supervised data, and scenarios characterized by zero-shot and federated data availability. Finally, we discuss related open questions, particularly concerning evaluation metrics, how the forgetting information is represented and delivered, and the unique challenges posed by large generative models.

Machine unlearning aims to enable models to forget specific data instances when receiving deletion requests. Current research centers on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts on the remaining data. Consequently, existing unlearning algorithms degrade the model's performance after unlearning, known as over-unlearning. This paper addresses this critical yet under-explored issue by introducing machine Unlearning via Null Space Calibration (UNSC), which can accurately unlearn target samples without over-unlearning. On the contrary, by calibrating the decision space during unlearning, UNSC can significantly improve the model's performance on the remaining samples. In particular, our approach hinges on confining the unlearning process to a specified null space tailored to the remaining samples, which is augmented by strategically pseudo-labeling the unlearning samples. Comparison against several established baselines affirms the superiority of our approach.

In recent years, there has been a growing interest in applying reinforcement learning (RL) techniques to order execution owing to RL’s strong sequential decision-making ability. However, realistic order execution tasks usually involve a large fine-grained action space and a long trading duration. The former hinders the RL agents from efficient exploration. The latter increases the task complexity, since the agent must capture price advantages throughout the day as well as micro changes within a few seconds on the limited order books. In addressing these challenges, we propose MacMic, a novel Hierarchical RL-based order execution approach that captures market patterns and executes orders from different temporal scales. MacMic employs a high-level agent to split the parent order into smaller slices at coarse-grained time steps. Then a low-level agent is adopted to execute these slices by placing fixed-size sub-orders at a continuous time. Besides, to balance the multifaceted objectives of the two tasks, MacMic pretrains a causal stacking hidden Markov model (SHMM) to obtain both effective macro-level and micro-level market states. Comprehensive experimental results on 200 stocks across the US and China A-share markets validate the effectiveness of the proposed method.

Both Transformer and Graph Neural Networks (GNNs) have been used in learning to rank (LTR), however, they adhere to two distinct yet complementary problem formulations, i.e., ranking score regression based on query-webpage pairs and link prediction within query-webpage bipartite graphs, respectively. Though it is possible to pre-train GNNs or Transformers on source datasets and fine-tune them subject to sparsely annotated LTR datasets separately, the source-target distribution shifts across the pairs and bipartite graphs domains make it extremely difficult to integrate these diverse models into a single LTR framework at a web-scale. We introduce the novel MPGraf model, which utilizes a modular and capsule-based pre-training approach, aiming to incorporate regression capacities from Transformers and link prediction capabilities of GNNs cohesively. We conduct extensive experiments to evaluate the performance of MPGraf using real-world datasets collected from large-scale search engines. The results show that MPGraf can outperform baseline algorithms on several major metrics. Further, we deploy and evaluate MPGraf atop a large-scale search engine with realistic web traffic via A/B tests, where we can still observe significant improvement. MPGraf performs consistently in both offline and online evaluations.

Reinforcement learning from visual observations is a challenging problem with many real-world applications. Existing algorithms mostly rely on a single observation from a well-designed fixed camera that requires human knowledge. Recent studies learn from different viewpoints with multiple fixed cameras, but this incurs high computation and storage costs and may not guarantee the coverage of the optimal viewpoint. To alleviate these limitations, we propose a straightforward View-conditional Partially Observable Markov Decision Processes (VPOMDPs) assumption and develop a new method, the MOdel-based SEnsor controlleR (MOSER). MOSER jointly learns a view-conditional world model (VWM) to simulate the environment, a sensory policy to control the camera, and a motor policy to complete tasks. We design intrinsic rewards from the VWM without additional modules to guide the sensory policy to adjust the camera parameters. Experiments on locomotion and manipulation tasks demonstrate that MOSER autonomously discovers task-specific viewpoints and significantly outperforms most baseline methods.

Document Question Answering (QA) presents a challenge in understanding visually-rich documents (VRD), particularly with lengthy textual content. Existing studies primarily focus on real-world documents with sparse text, while challenges persist in comprehending the hierarchical semantic relations among multiple pages to locate multimodal components. The paper introduces PDF-MVQA, tailored for research journal articles, encompassing multiple pages and multimodal retrieval. Our approach aims to retrieve entire paragraphs containing answers or visually rich document entities like tables and figures. The main contribution is introducing a comprehensive PDF Document VQA dataset, allowing the examination of semantically hierarchical layout structures in text-dominant documents. We also present new VRD-QA frameworks to grasp textual contents and relations among document layouts simultaneously, extending page-level understanding to the entire multi-page document. We aim to enhance the capabilities of existing vision-and-language models in handling challenges posed by text-dominant documents in VRD-QA. Code and Appendix are in https://github.com/adlnlp/pdfmvqa

In this paper, we address the challenge of accurately modeling and predicting Gibbs free energy in solute-solvent interactions, a pivotal yet complex aspect in the field of chemical modeling. Traditional approaches, primarily relying on deep learning models, face limitations in capturing the intricate dynamics of these interactions. To overcome these constraints, we introduce a novel framework, molecular modeling graph neural network (MMGNN), which more closely mirrors real-world chemical processes.Specifically, MMGNN explicitly models atomic interactions such as hydrogen bonds by initially forming indiscriminate connections between intermolecular atoms, which are then refined using an attention-based aggregation method, tailoring to specific solute-solvent pairs. To address the challenges of non-interactive or repulsive atomic interactions, MMGNN incorporates interpreters for nodes and edges in the merged graph, enhancing explainability and reducing redundancy. MMGNN stands as the first framework to explicitly align with real chemical processes, providing a more accurate and scientifically sound approach to modeling solute-solvent interactions. The infusion of explainability allows for the extraction of key subgraphs, which are pivotal for further research in solute-solvent dynamics. Extensive experimental validation confirms the efficacy and enhanced explainability of MMGNN.

Popular transformer-based detectors detect objects in a one-to-one manner, where both the bounding box and category of each object are predicted only by the single query, leading to the box-sensitive category predictions. Additionally, the initialization of positional queries solely based on the predicted confidence scores or learnable embeddings neglects the significant spatial interrelation between different queries. This oversight leads to an imbalanced spatial distribution of queries (SDQ). In this paper, we propose a new MLP-DINO model to address these issues. Firstly, we present a new Query-Independent Category Supervision (QICS) approach for modeling categories information, decoupling the sensitive bounding box prediction process to improve the detection performance. Additionally, to further improve the category predictions, we introduce a deep MLP model into transformer-based detection framework to capture the long-range and short-range information simultaneously. Thirdly, to balance the SDQ, we design a novel Graph-based Query Selection (GQS) method that distributes each query point in a discrete manner by graphing the spatial information of queries to cover a broader range of potential objects, significantly enhancing the hit-rate of queries. Experimental results on COCO indicate that our MLP-DINO achieves 54.6% AP with only 44M parame ters under 36-epoch setting, greatly outperforming the original DINO by +3.7% AP with fewer parameters and FLOPs. The source codes will be available at https://github.com/Med-Process/MLP-DINO.

Box supervised instance segmentation (BSIS) aims to achieve an effective trade-off between annotation costs and model performance by solely relying on bounding box annotations during training process. However, we observe that BSIS model is bottlenecked by the intricate objective under limited guidance, and tends to sacrifice segmentation capability in order to effectively recognize multiple instances. To boost the BSIS model's perceptual ability for object shape and contour, we introduce MISA, that is, MIning Saliency-Aware semantic prior from a well-optimized box supervised semantic segmentation (BSSS) network, and incorporating cross-model guidance into the learning process of BSIS. Specifically, we first design a Frequency-Space Distillation (FSD) module to extract assorted salient prior knowledge from BSSS model, and perform cross-model alignment for transfering the prior to BSIS model. Furthermore, we introduce Semantic-Enhanced Pairwise Affinity (SEPA), which borrows the object perceptual ability of BSSS model to emphasize the contribution of salient objects for pairwise affinity, providing more accurate guidance for the BSIS network. Extensive experiments show that our proposed MISA consistently surpasses the existing state-of-the-art methods by a large margin in the BSIS scenario.

Offline reinforcement learning (RL) faces a significant challenge of distribution shift. Model-free offline RL penalizes the Q value for out-of-distribution (OOD) data or constrains the policy closed to the behavior policy to tackle this problem, but this inhibits the exploration of the OOD region. Model-based offline RL, which uses the trained environment model to generate more OOD data and performs conservative policy optimization within that model, has become an effective method for this problem. However, the current model-based algorithms rarely consider agent robustness when incorporating conservatism into policy. Therefore, the new model-based offline algorithm with a conservative Bellman operator (MICRO) is proposed. This method trades off performance and robustness via introducing the robust Bellman operator into the algorithm. Compared with previous model-based algorithms with robust adversarial models, MICRO can significantly reduce the computation cost by only choosing the minimal Q value in the state uncertainty set. Extensive experiments demonstrate that MICRO outperforms prior RL algorithms in offline RL benchmark and is considerably robust to adversarial perturbations.

With the expansion of the scale of robotics applications, the multi-goal multi-agent pathfinding (MG-MAPF) problem began to gain widespread attention. This problem requires each agent to visit pre-assigned multiple goal points at least once without conflict. Some previous methods have been proposed to solve the MG-MAPF problem based on Decoupling the goal Vertex visiting order search and the Single-agent pathfinding (DVS). However, this paper demonstrates that the methods based on DVS cannot always obtain the optimal solution. To obtain the optimal result, we propose the Multi-Goal Conflict-Based Search (MGCBS), which is based on Decoupling the goal Safe interval visiting order search and the Single-agent pathfinding (DSS). Additionally, we present the Time-Interval-Space Forest (TIS Forest) to enhance the efficiency of MGCBS by maintaining the shortest paths from any start point at any start time step to each safe interval at the goal points. The experiment demonstrates that our method can consistently obtain optimal results and execute up to 7 times faster than the state-of-the-art method in our evaluation.

This paper introduces a trajectory prediction model tailored for autonomous driving, focusing on capturing complex interactions in dynamic traffic scenarios without reliance on high-definition maps. The model, termed MFTraj, harnesses historical trajectory data combined with a novel dynamic geometric graph-based behavior-aware module. At its core, an adaptive structure-aware interactive graph convolutional network captures both positional and behavioral features of road users, preserving spatial-temporal intricacies. Enhanced by a linear attention mechanism, the model achieves computational efficiency and reduced parameter overhead. Evaluations on the Argoverse, NGSIM, HighD, and MoCAD datasets underscore MFTraj's robustness and adaptability, outperforming numerous benchmarks even in data-challenged scenarios without the need for additional information such as HD maps or vectorized maps. Importantly, it maintains competitive performance even in scenarios with substantial missing data (12.5%-50%), outperforming most existing state-of-the-art models. The results and methodology suggest a significant advancement in autonomous driving trajectory prediction, paving the way for safer and efficient autonomous systems.

This work presents a dynamic vocabulary adaptation strategy, MEDVOC, for fine-tuning pre-trained language models (PLMs) like BertSumAbs, BART, and PEGASUS for improved medical text summarization. In contrast to existing domain adaptation approaches in summarization, MEDVOC treats vocabulary as an optimizable parameter and optimizes the PLM vocabulary based on fragment score conditioned only on the downstream task's reference summaries. Unlike previous works on vocabulary adaptation (limited only to classification tasks), optimizing vocabulary based on summarization tasks requires an extremely costly intermediate fine-tuning step on large summarization datasets. To that end, our novel fragment score-based hyperparameter search very significantly reduces this fine-tuning time --- from 450 days to less than 2 days on average. Furthermore, while previous works on vocabulary adaptation are often primarily tied to single PLMs, MEDVOC is designed to be deployable across multiple PLMs (with varying model vocabulary sizes, pre-training objectives, and model sizes) --- bridging the limited vocabulary overlap between the biomedical literature domain and PLMs. MEDVOC outperforms baselines by 15.74% in terms of Rouge-L in zero-shot setting and shows gains of 17.29% in high Out-Of-Vocabulary (OOV) concentrations. Our human evaluation shows MEDVOC generates more faithful medical summaries (88% compared to 59% in baselines).

Conditional human motion synthesis (HMS) aims to generate human motion sequences that conform to specific conditions. Text and audio represent the two predominant modalities employed as HMS control conditions. While existing research has primarily focused on single conditions, the multi-condition human motion synthesis remains underexplored. In this study, we propose a multi-condition HMS framework, termed MCM, based on a dual-branch structure composed of a main branch and a control branch. This framework effectively extends the applicability of the diffusion model, which is initially predicated solely on textual conditions, to auditory conditions. This extension encompasses both music-to-dance and co-speech HMS while preserving the intrinsic quality of motion and the capabilities for semantic association inherent in the original model. Furthermore, we propose the implementation of a Transformer-based diffusion model, designated as MWNet, as the main branch. This model adeptly apprehends the spatial intricacies and inter-joint correlations inherent in motion sequences, facilitated by the integration of multi-wise self-attention modules. Extensive experiments show that our method achieves competitive results in single-condition and multi-condition HMS tasks.

Recently, Segment Anything Model (SAM) shows exceptional performance in generating high-quality object masks and achieving zero-shot image segmentation. However, as a versatile vision model, SAM is primarily trained with large-scale natural light images. In underwater scenes, it exhibits substantial performance degradation due to the light scattering and absorption. Meanwhile, the simplicity of the SAM's decoder might lead to the loss of fine-grained object details. To address the above issues, we propose a novel feature learning framework named MAS-SAM for marine animal segmentation, which involves integrating effective adapters into the SAM's encoder and constructing a pyramidal decoder. More specifically, we first build a new SAM's encoder with effective adapters for underwater scenes. Then, we introduce a Hypermap Extraction Module (HEM) to generate multi-scale features for a comprehensive guidance. Finally, we propose a Progressive Prediction Decoder (PPD) to aggregate the multi-scale features and predict the final segmentation results. When grafting with the Fusion Attention Module (FAM), our method enables to extract richer marine information from global contextual cues to fine-grained local details. Extensive experiments on four public MAS datasets demonstrate that our MAS-SAM can obtain better results than other typical segmentation methods. The source code is available at https://github.com/Drchip61/MAS-SAM.

Precise perception of articulated objects is vital for empowering service robots. Recent studies mainly focus on point cloud, a single-modal approach, often neglecting vital texture and lighting details and assuming ideal conditions like optimal viewpoints, unrepresentative of real-world scenarios. To address these limitations, we introduce MARS, a novel framework for articulated object characterization. It features a multi-modal fusion module utilizing multi-scale RGB features to enhance point cloud features, coupled with reinforcement learning-based active sensing for autonomous optimization of observation viewpoints. In experiments conducted with various articulated object instances from the PartNet-Mobility dataset, our method outperformed current state-of-the-art methods in joint parameter estimation accuracy. Additionally, through active sensing, MARS further reduces errors, demonstrating enhanced efficiency in handling suboptimal viewpoints. Furthermore, our method effectively generalizes to real-world articulated objects, enhancing robot interactions. Code is available at https://github.com/robhlzeng/MARS.

Neural Combinatorial Optimization (NCO) is an emerging domain where deep learning techniques are employed to address combinatorial optimization problems as a standalone solver. Despite their potential, existing NCO methods often suffer from inefficient search space exploration, frequently leading to local optima entrapment or redundant exploration of previously visited states. This paper introduces a versatile framework, referred to as Memory-Augmented Reinforcement for Combinatorial Optimization (MARCO), that can be used to enhance both constructive and improvement methods in NCO through an innovative memory module. MARCO stores data collected throughout the optimization trajectory and retrieves contextually relevant information at each state. This way, the search is guided by two competing criteria: making the best decision in terms of the quality of the solution and avoiding revisiting already explored solutions. This approach promotes a more efficient use of the available optimization budget. Moreover, thanks to the parallel nature of NCO models, several search threads can run simultaneously, all sharing the same memory module, enabling an efficient collaborative exploration. Empirical evaluations, carried out on the maximum cut, maximum independent set and travelling salesman problems, reveal that the memory module effectively increases the exploration, enabling the model to discover diverse, higher-quality solutions. MARCO achieves good performance in a low computational cost, establishing a promising new direction in the field of NCO.

Distributed deep reinforcement learning (DDRL) has gained increasing attention due to the emerging requirements for addressing complex games like Go and StarCraft. However, how to effectively and stably train bots with asynchronous and heterogeneous agents cooperation and competition for multiple players under multiple machines (with multiple CPUs and GPUs) using DDRL is still an open problem. We propose and open M2RL, a Multi-player and Multi-agent Reinforcement Learning framework, to make training bots for complex games an easy-to-use warehouse. Experiments involving training a two-player multi-agent Wargame AI, and a sixteen-player multi-agent community game Neural MMO AI, demonstrate the effectiveness of the proposed framework by winning a silver award and beating high-level AI bots designed by professional players.