AAAI 2024 Papers

The COVID-19 pandemic has exacerbated the challenges faced by healthcare delivery in developing nations, placing additional strain on already fragile infrastructure and healthcare systems. This has prompted an increased reliance on lay healthcare workers (LHWs) to meet the surging demand for services. Due to limited formal training, many LHWs have resorted to using unreliable sources, such as internet searches, to access medical information. Large language models (LLMs) offer a promising opportunity to support LHWs by providing accurate, context-sensitive information for improving healthcare delivery, provided they are appropriately fine-tuned on domain-specific multilingual data. This paper delves into critical issues and presents potential solutions for developing LLM-powered virtual assistants tailored to LHWs serving Telugu and Hindi-speaking populations. Key focal points include the customization of language and content to suit local contexts, the integration of feedback mechanisms to continuously enhance assistance quality, and the delicate balance between automation and human oversight.

Prediction of drug-target interactions (DTIs) is a crucial step in drug discovery, and deep learning methods have shown great promise on various DTI datasets. However, existing approaches still face several challenges, including limited labeled data, hidden bias issue, and a lack of generalization ability to out-of-domain data. These challenges hinder the model's capacity to learn truly informative interaction features, leading to shortcut learning and inferior predictive performance on novel drug-target pairs. To address these issues, we propose MlanDTI, a semi-supervised domain adaptive multilevel attention network (Mlan) for DTI prediction. We utilize two pre-trained BERT models to acquire bidirectional representations enriched with information from unlabeled data. Then, we introduce a multilevel attention mechanism, enabling the model to learn domain-invariant DTIs at different hierarchical levels. Moreover, we present a simple yet effective semi-supervised pseudo-labeling method to further enhance our model's predictive ability in cross-domain scenarios. Experiments on four datasets show that MlanDTI achieves state-of-the-art performances over other methods under intra-domain settings and outperforms all other approaches under cross-domain settings. The source code is available at https://github.com/CMACH508/MlanDTI.

Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the scarcity of labeled multichannel data and complex ambient noises. The efficacy of self-supervised learning for far-field multichannel and multi-modal speech processing has not been well explored. Considering that visual information helps to improve speech recognition performance in noisy scenes, in this work we propose the multichannel multi-modal speech self-supervised learning framework AV-wav2vec2, which utilizes video and multichannel audio data as inputs. First, we propose a multi-path structure to process multi-channel audio streams and a visual stream in parallel, with intra-, and inter-channel contrastive as training targets to fully exploit the rich information in multi-channel speech data. Second, based on contrastive learning, we use additional single-channel audio data, which is trained jointly to improve the performance of multichannel multi-modal representation. Finally, we use a Chinese multichannel multi-modal dataset in real scenarios to validate the effectiveness of the proposed method on audio-visual speech recognition (AVSR), automatic speech recognition (ASR), visual speech recognition (VSR) and audio-visual speaker diarization (AVSD) tasks.

AlphaZero and MuZero have achieved state-of-the-art (SOTA) performance in a wide range of domains, including board games and robotics, with discrete and continuous action spaces. However, to obtain an improved policy, they often require an excessively large number of simulations, especially for domains with large action spaces. As the simulation budget decreases, their performance drops significantly. In addition, many important real-world applications have combinatorial (or exponential) action spaces, making it infeasible to search directly over all possible actions. In this paper, we extend AlphaZero and MuZero to learn and plan in more complex multiagent (MA) Markov decision processes, where the action spaces increase exponentially with the number of agents. Our new algorithms, MA Gumbel AlphaZero and MA Gumbel MuZero, respectively without and with model learning, achieve superior performance on cooperative multiagent control problems, while reducing the number of environmental interactions by up to an order of magnitude compared to model-free approaches. In particular, we significantly improve prior performance when planning with much fewer simulation budgets. The code and appendix are available at https://github.com/tjuHaoXiaotian/MA-MuZero.

Social summarization aims to provide summaries for a large number of social texts (called posts) about a single topic. To extract a summary, both the representation of post and summary selection method are crucial. Previous methods introduce social relation to enhance post embedding to mitigate the sparse representation due to its brief and informal expression. However, they ignore that there are multiple relations between posts. Besides, existing graph-based centrality calculation approaches tend to select posts from one aspect. This leads to facet bias especially when there are multiple viewpoints. In this paper, we propose a model named MultiSum to improve social summarization. Specifically, 1) We use graph convolutional networks to fuse text content with social and semantic relations to improve post representation; 2) The similarity between the summary and all aspects is incorporated into the centrality score during the selection phase, encouraging the model to pay attention to different facets. Experimental results on English and Chinese corpora support the effectiveness of this model. Furthermore, external evaluations by human experts and large language models demonstrate the validity of MultiSum in facet coverage and redundancy reduction.

World Models are made of generative networks that can predict future states of a single environment which it was trained on. This research proposes a Multi-world Model, a foundational model built from World Models for the field of continual reinforcement learning that is trained on many different environments, enabling it to generalize state sequence predictions even for unseen settings.

Multi kernel learning (MKL) is a representative supervised multi-view learning method widely applied in multi-modal and multi-view applications. MKL aims to classify data by integrating complementary information from predefined kernels. Although existing MKL methods achieve promising performance, they fail to consider the tradeoff between diversity and classification accuracy of kernels, preventing further improvement of classification performance. In this paper, we tackle this problem by generating a number of high-quality base learning kernels and selecting a kernel subset with maximum pairwise diversity and minimum generalization errors. We first formulate this idea as a nonconvex quadratic integer programming problem. Then we transform this nonconvex problem into a convex optimization problem and prove it is equivalent to a semidefinite relaxation problem, which a semidefinite-based branch-and-bound algorithm can quickly solve. Experimental results on the real-world datasets demonstrate the superiority of the proposed method. The results also show that our method works for the support vector machine (SVM) classifier and other state-of-the-art kernel classifiers.

Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view frames and fixed camera views. As a result, these methods may not be practical for detecting people in larger, more complex scenes with severe occlusions and camera calibration errors. This paper focuses on improving multi-view people detection by developing a supervised view-wise contribution weighting approach that better fuses multi-camera information under large scenes. Besides, a large synthetic dataset is adopted to enhance the model's generalization ability and enable more practical evaluation and comparison. The model's performance on new testing scenes is further improved with a simple domain adaptation technique. Experimental results demonstrate the effectiveness of our approach in achieving promising cross-scene multi-view people detection performance.

Recent research has shown significant interest in image-based glass surface detection (GSD). However, detecting glass surfaces in dynamic scenes remains largely unexplored due to the lack of a high-quality dataset and an effective video glass surface detection (VGSD) method. In this paper, we propose the first VGSD approach. Our key observation is that reflections frequently appear on glass surfaces, but they change dynamically as the camera moves. Based on this observation, we propose to offset the excessive dependence on a single uncertainty reflection via joint modeling of temporal and spatial reflection cues. To this end, we propose the VGSD-Net with two novel modules: a Location-aware Reflection Extraction (LRE) module and a Context-enhanced Reflection Integration (CRI) module, for the position-aware reflection feature extraction and the spatial-temporal reflection cues integration, respectively. We have also created the first large-scale video glass surface dataset (VGSD-D), consisting of 19,166 image frames with accurately-annotated glass masks extracted from 297 videos. Extensive experiments demonstrate that VGSD-Net outperforms state-of-the-art approaches adapted from related fields. Code and dataset will be available at https://github.com/fawnliu/VGSD.

Denoising Diffusion Probabilistic Models (DDPMs) have achieved significant success in generation tasks. Nevertheless, the exposure bias issue, i.e., the natural discrepancy between the training (the output of each step is calculated individually by a given input) and inference (the output of each step is calculated based on the input iteratively obtained based on the model), harms the performance of DDPMs. To our knowledge, few works have tried to tackle this issue by modifying the training process for DDPMs, but they still perform unsatisfactorily due to 1) partially modeling the discrepancy and 2) ignoring the prediction error accumulation. To address the above issues, in this paper, we propose a multi-step denoising scheduled sampling (MDSS) strategy to alleviate the exposure bias for DDPMs. Analyzing the formulations of the training and inference of DDPMs, MDSS 1) comprehensively considers the discrepancy influence of prediction errors on the output of the model (the Gaussian noise) and the output of the step (the calculated input signal of the next step), and 2) efficiently models the prediction error accumulation by using multiple iterations of a mathematical formulation initialized from one-step prediction error obtained from the model. The experimental results, compared with previous works, demonstrate that our approach is more effective in mitigating exposure bias in DDPM, DDIM, and DPM-solver. In particular, MDSS achieves an FID score of 3.86 in 100 sample steps of DDIM on the CIFAR-10 dataset, whereas the second best obtains 4.78. The code will be available on GitHub.

Traditional business processes such as loan processing, order processing, or procurement have a series of steps that are pre-defined at design and executed by enterprise systems. Recent advancements in new-age businesses, however, focus on having adaptive and ad-hoc processes by stitching together a set of functions or steps enabled through autonomous agents. Further, to enable business users to execute a flexible set of steps, there have been works on providing a conversational interface to interact and execute automation. Often, it is necessary to guide the user through the set of possible steps in the process (or workflow). Existing work on recommending the next agent to run relies on historical data. However, with changing workflows and new automation constantly getting added, it is important to provide recommendations without historical data. Additionally, hand-crafted recommendation rules do not scale. The adaptive workflow being a combination of structured and unstructured information, makes it harder to mine. Hence, in this work, we leverage Large Language Models (LLMs) to combine process knowledge with the meta-data of agents to discover NBAs specifically at cold-start. We propose a multi-stage approach that uses existing process knowledge and agent meta-data information to prompt LLM and recommend meaningful next best agent (NBA) based on user utterances.

Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain. Due to privacy concerns, the data from different source domains are kept isolated, which poses challenges in bridging the domain gap. To address this issue, we propose a Multi-source Collaborative Gradient Discrepancy Minimization (MCGDM) method for federated domain generalization. Specifically, we propose intra-domain gradient matching between the original images and augmented images to avoid overfitting the domain-specific information within isolated domains. Additionally, we propose inter-domain gradient matching with the collaboration of other domains, which can further reduce the domain shift across decentralized domains. Combining intra-domain and inter-domain gradient matching, our method enables the learned model to generalize well on unseen domains. Furthermore, our method can be extended to the federated domain adaptation task by fine-tuning the target model on the pseudo-labeled target domain. The extensive experiments on federated domain generalization and adaptation indicate that our method outperforms the state-of-the-art methods significantly.

The global multi-object tracking (MOT) system can consider interaction, occlusion, and other ``visual blur'' scenarios to ensure effective object tracking in long videos. Among them, graph-based tracking-by-detection paradigms achieve surprising performance. However, their fully-connected nature poses storage space requirements that challenge algorithm handling long videos. Currently, commonly used methods are still generated trajectories by building one-forward associations across frames. Such matches produced under the guidance of first-order similarity information may not be optimal from a longer-time perspective. Moreover, they often lack an end-to-end scheme for correcting mismatches. This paper proposes the Composite Node Message Passing Network (CoNo-Link), a multi-scene generalized framework for modeling ultra-long frames information for association. CoNo-Link's solution is a low-storage overhead method for building constrained connected graphs. In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction, improving the graph neural network's feature representation capability. Specifically, we formulate the graph-building problem as a top-k selection task for some reliable objects or trajectories. Our model can learn better predictions on longer-time scales by adding composite nodes. As a result, our method outperforms the state-of-the-art in several commonly used datasets.

The success of graph neural networks (GNNs) has spurred numerous new works leveraging GNNs for modeling multivariate time series anomaly detection. Despite their achieved performance improvements, most of them only consider static graph to describe the spatial-temporal dependencies between time series. Moreover, existing works neglect the time and scale-changing structures of time series. In this work, we propose MDGAD, a novel multi-scale dynamic graph structure learning approach for time series anomaly detection. We design a multi-scale graph structure learning module that captures the complex correlations among time series, constructing an evolving graph at each scale. Meanwhile, an anomaly detector is used to combine bilateral prediction errors to detect abnormal data. Experiments conducted on two time series datasets demonstrate the effectiveness of MDGAD.

Text-guided image manipulation has attracted significant attention recently. Prevailing techniques concentrate on image attribute editing for individual objects, however, encountering challenges when it comes to multi-object editing. The main reason is the lack of consistency constraints on the spatial layout. This work presents a multi-region guided image manipulation framework, enabling manipulation through region-level textual prompts. With MultiDiffusion as a baseline, we are dedicated to the automatic generation of a rational multi-object spatial distribution, where disparate regions are fused as a unified entity. To mitigate interference from regional fusion, we employ an off-the-shelf model (CLIP) to impose region-aware spatial guidance on multi-object manipulation. Moreover, when applied to the StableDiffusion, the presence of quality-related yet object-agnostic lengthy words hampers the manipulation. To ensure focus on meaningful object-specific words for efficient guidance and generation, we introduce a keyword selection method. Furthermore, we demonstrate a downstream application of our method for multi-region inversion, which is tailored for manipulating multiple objects in real images. Our approach, compatible with variants of Stable Diffusion models, is readily applicable for manipulating diverse objects in extensive images with high-quality generation, showing superb image control capabilities. Code is available at https://github.com/liyiming09/multi-region-guided-diffusion.

In the domain of scene graph generation, modeling commonsense as a single-prototype representation has been typically employed to facilitate the recognition of infrequent predicates. However, a fundamental challenge lies in the large intra-class variations of the visual appearance of predicates, resulting in subclasses within a predicate class. Such a challenge typically leads to the problem of misclassifying diverse predicates due to the rough predicate space clustering. In this paper, inspired by cognitive science, we maintain multi-prototype representations for each predicate class, which can accurately find the multiple class centers of the predicate space. Technically, we propose a novel multi-prototype learning framework consisting of three main steps: prototype-predicate matching, prototype updating, and prototype space optimization. We first design a triple-level optimal transport to match each predicate feature within the same class to a specific prototype. In addition, the prototypes are updated using momentum updating to find the class centers according to the matching results. Finally, we enhance the inter-class separability of the prototype space through iterations of the inter-class separability loss and intra-class compactness loss. Extensive evaluations demonstrate that our approach significantly outperforms state-of-the-art methods on the Visual Genome dataset.

The fine-grained attribute descriptions can significantly supplement the valuable semantic information for person image, which is vital to the success of person re-identification (ReID) task. However, current ReID algorithms typically failed to effectively leverage the rich contextual information available, primarily due to their reliance on simplistic and coarse utilization of image attributes. Recent advances in artificial intelligence generated content have made it possible to automatically generate plentiful fine-grained attribute descriptions and make full use of them. Thereby, this paper explores the potential of using the generated multiple person attributes as prompts in ReID tasks with off-the-shelf (large) models for more accurate retrieval results. To this end, we present a new framework called Multi-Prompts ReID (MP-ReID), based on prompt learning and language models, to fully dip fine attributes to assist ReID task. Specifically, MP-ReID first learns to hallucinate diverse, informative, and promptable sentences for describing the query images. This procedure includes (i) explicit prompts of which attributes a person has and furthermore (ii) implicit learnable prompts for adjusting/conditioning the criteria used towards this person identity matching. Explicit prompts are obtained by ensembling generation models, such as ChatGPT and VQA models. Moreover, an alignment module is designed to fuse multi-prompts (i.e., explicit and implicit ones) progressively and mitigate the cross-modal gap. Extensive experiments on the existing attribute-involved ReID datasets, namely, Market1501 and DukeMTMC-reID, demonstrate the effectiveness and rationality of the proposed MP-ReID solution.

There are a lot of real-world black-box optimization problems that need to optimize multiple criteria simultaneously. However, in a multi-objective optimization (MOO) problem, identifying the whole Pareto front requires the prohibitive search cost, while in many practical scenarios, the decision maker (DM) only needs a specific solution among the set of the Pareto optimal solutions. We propose a Bayesian optimization (BO) approach to identifying the most preferred solution in the MOO with expensive objective functions, in which a Bayesian preference model of the DM is adaptively estimated by an interactive manner based on the two types of supervisions called the pairwise preference and improvement request. To explore the most preferred solution, we define an acquisition function in which the uncertainty both in the objective function and the DM preference is incorporated. Further, to minimize the interaction cost with the DM, we also propose an active learning strategy for the preference estimation. We empirically demonstrate the effectiveness of our proposed method through the benchmark function optimization and the hyper-parameter optimization problems for machine learning models.

3D point cloud semantic segmentation has a wide range of applications. Recently, weakly supervised point cloud segmentation methods have been proposed, aiming to alleviate the expensive and laborious manual annotation process by leveraging scene-level labels. However, these methods have not effectively exploited the rich geometric information (such as shape and scale) and appearance information (such as color and texture) present in RGB-D scans. Furthermore, current approaches fail to fully leverage the point affinity that can be inferred from the feature extraction network, which is crucial for learning from weak scene-level labels. Additionally, previous work overlooks the detrimental effects of the long-tailed distribution of point cloud data in weakly supervised 3D semantic segmentation. To this end, this paper proposes a simple yet effective scene-level weakly supervised point cloud segmentation method with a newly introduced multi-modality point affinity inference module. The point affinity proposed in this paper is characterized by features from multiple modalities (e.g., point cloud and RGB), and is further refined by normalizing the classifier weights to alleviate the detrimental effects of long-tailed distribution without the need of the prior of category distribution. Extensive experiments on the ScanNet and S3DIS benchmarks verify the effectiveness of our proposed method, which outperforms the state-of-the-art by ~4% to ~ 6% mIoU. Codes are released at https://github.com/Sunny599/AAAI24-3DWSSG-MMA.