Junbo Zhang

Jiahao Ji, Jingyuan Wang, Chao Huang et al.

Robust prediction of citywide traffic flows at different time periods plays a crucial role in intelligent transportation systems. While previous work has made great efforts to model spatio-temporal correlations, existing methods still suffer from two key limitations: i) Most models collectively predict all regions' flows without accounting for spatial heterogeneity, i.e., different regions may have skewed traffic flow distributions. ii) These models fail to capture the temporal heterogeneity induced by time-varying traffic patterns, as they typically model temporal correlations with a shared parameterized space for all time periods. To tackle these challenges, we propose a novel Spatio-Temporal Self-Supervised Learning (ST-SSL) traffic prediction framework which enhances the traffic pattern representations to be reflective of both spatial and temporal heterogeneity, with auxiliary self-supervised learning paradigms. Specifically, our ST-SSL is built over an integrated module with temporal and spatial convolutions for encoding the information across space and time. To achieve the adaptive spatio-temporal self-supervised learning, our ST-SSL first performs the adaptive augmentation over the traffic flow graph data at both attribute- and structure-levels. On top of the augmented traffic graph, two SSL auxiliary tasks are constructed to supplement the main traffic prediction task with spatial and temporal heterogeneity-aware augmentation. Experiments on four benchmark datasets demonstrate that ST-SSL consistently outperforms various state-of-the-art baselines. Since spatio-temporal heterogeneity widely exists in practical datasets, the proposed framework may also cast light on other spatial-temporal applications. Model implementation is available at https://github.com/Echo-Ji/ST-SSL.

Yuxuan Liang, Yutong Xia, Songyu Ke et al.

Air pollution is a crucial issue affecting human health and livelihoods, as well as one of the barriers to economic and social growth. Forecasting air quality has become an increasingly important endeavor with significant social impacts, especially in emerging countries like China. In this paper, we present a novel Transformer architecture termed AirFormer to collectively predict nationwide air quality in China, with an unprecedented fine spatial granularity covering thousands of locations. AirFormer decouples the learning process into two stages -- 1) a bottom-up deterministic stage that contains two new types of self-attention mechanisms to efficiently learn spatio-temporal representations; 2) a top-down stochastic stage with latent variables to capture the intrinsic uncertainty of air quality data. We evaluate AirFormer with 4-year data from 1,085 stations in the Chinese Mainland. Compared to the state-of-the-art model, AirFormer reduces prediction errors by 5%~8% on 72-hour future predictions. Our source code is available at https://github.com/yoshall/airformer.

Junbo Zhang, Guofan Fan, Guanghan Wang et al. · tsinghua

Learning descriptive 3D features is crucial for understanding 3D scenes with diverse objects and complex structures. However, it is usually unknown whether important geometric attributes and scene context obtain enough emphasis in an end-to-end trained 3D scene understanding network. To guide 3D feature learning toward important geometric attributes and scene context, we explore the help of textual scene descriptions. Given some free-form descriptions paired with 3D scenes, we extract the knowledge regarding the object relationships and object attributes. We then inject the knowledge to 3D feature learning through three classification-based auxiliary tasks. This language-assisted training can be combined with modern object detection and instance segmentation methods to promote 3D semantic scene understanding, especially in a label-deficient regime. Moreover, the 3D feature learned with language assistance is better aligned with the language features, which can benefit various 3D-language multimodal tasks. Experiments on several benchmarks of 3D-only and 3D-language tasks demonstrate the effectiveness of our language-assisted 3D feature learning. Code is available at https://github.com/Asterisci/Language-Assisted-3D.

Runpei Dong, Zekun Qi, Linfeng Zhang et al.

The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-modal knowledge transferring. In this paper, we revisit masked modeling in a unified fashion of knowledge distillation, and we show that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Modal Teachers (ACT). The pretrained Transformers are transferred as cross-modal 3D teachers using discrete variational autoencoding self-supervision, during which the Transformers are frozen with prompt tuning for better knowledge inheritance. The latent features encoded by the 3D teachers are used as the target of masked point modeling, wherein the dark knowledge is distilled to the 3D Transformer students as foundational geometry understanding. Our ACT pretrained 3D learner achieves state-of-the-art generalization capacity across various downstream benchmarks, e.g., 88.21% overall accuracy on ScanObjectNN. Codes have been released at https://github.com/RunpeiDong/ACT.

Guangyin Jin, Yuxuan Liang, Yuchen Fang et al.

With recent advances in sensing technologies, a myriad of spatio-temporal data has been generated and recorded in smart cities. Forecasting the evolution patterns of spatio-temporal data is an important yet demanding aspect of urban computing, which can enhance intelligent management decisions in various fields, including transportation, environment, climate, public safety, healthcare, and others. Traditional statistical and deep learning methods struggle to capture complex correlations in urban spatio-temporal data. To this end, Spatio-Temporal Graph Neural Networks (STGNN) have been proposed, achieving great promise in recent years. STGNNs enable the extraction of complex spatio-temporal dependencies by integrating graph neural networks (GNNs) and various temporal learning methods. In this manuscript, we provide a comprehensive survey on recent progress on STGNN technologies for predictive learning in urban computing. Firstly, we provide a brief introduction to the construction methods of spatio-temporal graph data and the prevalent deep-learning architectures used in STGNNs. We then sort out the primary application domains and specific predictive learning tasks based on existing literature. Afterward, we scrutinize the design of STGNNs and their combination with some advanced technologies in recent years. Finally, we conclude the limitations of existing research and suggest potential directions for future work.

Peng Xie, Minbo Ma, Tianrui Li et al.

Urban metro flow prediction is of great value for metro operation scheduling, passenger flow management and personal travel planning. However, it faces two main challenges. First, different metro stations, e.g. transfer stations and non-transfer stations, have unique traffic patterns. Second, it is challenging to model complex spatio-temporal dynamic relation of metro stations. To address these challenges, we develop a spatio-temporal dynamic graph relational learning model (STDGRL) to predict urban metro station flow. First, we propose a spatio-temporal node embedding representation module to capture the traffic patterns of different stations. Second, we employ a dynamic graph relationship learning module to learn dynamic spatial relationships between metro stations without a predefined graph adjacency matrix. Finally, we provide a transformer-based long-term relationship prediction module for long-term metro flow prediction. Extensive experiments are conducted based on metro data in Beijing, Shanghai, Chongqing and Hangzhou. Experimental results show the advantages of our method beyond 11 baselines for urban metro flow prediction.

Junbo Zhang, Runpei Dong, Kaisheng Ma

Training a 3D scene understanding model requires complicated human annotations, which are laborious to collect and result in a model only encoding close-set object semantics. In contrast, vision-language pre-training models (e.g., CLIP) have shown remarkable open-world reasoning properties. To this end, we propose directly transferring CLIP's feature space to 3D scene understanding model without any form of supervision. We first modify CLIP's input and forwarding process so that it can be adapted to extract dense pixel features for 3D scene contents. We then project multi-view image features to the point cloud and train a 3D scene understanding model with feature distillation. Without any annotations or additional training, our model achieves promising annotation-free semantic segmentation results on open-vocabulary semantics and long-tailed concepts. Besides, serving as a cross-modal pre-training framework, our method can be used to improve data efficiency during fine-tuning. Our model outperforms previous SOTA methods in various zero-shot and data-efficient learning benchmarks. Most importantly, our model successfully inherits CLIP's rich-structured knowledge, allowing 3D scene understanding models to recognize not only object concepts but also open-world semantics.

Junbo Zhang, Kaisheng Ma

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings two drawbacks. First, the artificial choice of augmentation types brings specific representational invariances to the model, which have different degrees of positive and negative effects on different downstream tasks. Treating each type of augmentation equally during training makes the model learn non-optimal representations for various downstream tasks and limits the flexibility to choose augmentation types beforehand. Second, the strong data augmentations used in classic contrastive learning methods may bring too much invariance in some cases, and fine-grained information that is essential to some downstream tasks may be lost. This paper proposes a general method to alleviate these two problems by considering where and what to contrast in a general contrastive learning framework. We first propose to learn different augmentation invariances at different depths of the model according to the importance of each data augmentation instead of learning representational invariances evenly in the backbone. We then propose to expand the contrast content with augmentation embeddings to reduce the misleading effects of strong data augmentations. Experiments based on several baseline methods demonstrate that we learn better representations for various benchmarks on classification, detection, and segmentation downstream tasks.

Linfeng Zhang, Xin Chen, Junbo Zhang et al.

The success of deep learning is usually accompanied by the growth in neural network depth. However, the traditional training method only supervises the neural network at its last layer and propagates the supervision layer-by-layer, which leads to hardship in optimizing the intermediate layers. Recently, deep supervision has been proposed to add auxiliary classifiers to the intermediate layers of deep neural networks. By optimizing these auxiliary classifiers with the supervised task loss, the supervision can be applied to the shallow layers directly. However, deep supervision conflicts with the well-known observation that the shallow layers learn low-level features instead of task-biased high-level semantic features. To address this issue, this paper proposes a novel training framework named Contrastive Deep Supervision, which supervises the intermediate layers with augmentation-based contrastive learning. Experimental results on nine popular datasets with eleven models demonstrate its effects on general image classification, fine-grained image classification and object detection in supervised learning, semi-supervised learning and knowledge distillation. Codes have been released in Github.

Zijian Zhang, Ze Huang, Zhiwei Hu et al.

Traffic prediction is a typical spatio-temporal data mining task and has great significance to the public transportation system. Considering the demand for its grand application, we recognize key factors for an ideal spatio-temporal prediction method: efficient, lightweight, and effective. However, the current deep model-based spatio-temporal prediction solutions generally own intricate architectures with cumbersome optimization, which can hardly meet these expectations. To accomplish the above goals, we propose an intuitive and novel framework, MLPST, a pure multi-layer perceptron architecture for traffic prediction. Specifically, we first capture spatial relationships from both local and global receptive fields. Then, temporal dependencies in different intervals are comprehensively considered. Through compact and swift MLP processing, MLPST can well capture the spatial and temporal dependencies while requiring only linear computational complexity, as well as model parameters that are more than an order of magnitude lower than baselines. Extensive experiments validated the superior effectiveness and efficiency of MLPST against advanced baselines, and among models with optimal accuracy, MLPST achieves the best time and space efficiency.

Gaode Chen, Yijun Su, Xinghua Zhang et al.

Data insufficiency problems (i.e., data missing and label scarcity) caused by inadequate services and infrastructures or imbalanced development levels of cities have seriously affected the urban computing tasks in real scenarios. Prior transfer learning methods inspire an elegant solution to the data insufficiency, but are only concerned with one kind of insufficiency issue and fail to give consideration to both sides. In addition, most previous cross-city transfer methods overlook inter-city data privacy which is a public concern in practical applications. To address the above challenging problems, we propose a novel Cross-city Federated Transfer Learning framework (CcFTL) to cope with the data insufficiency and privacy problems. Concretely, CcFTL transfers the relational knowledge from multiple rich-data source cities to the target city. Besides, the model parameters specific to the target task are firstly trained on the source data and then fine-tuned to the target city by parameter transfer. With our adaptation of federated training and homomorphic encryption settings, CcFTL can effectively deal with the data privacy problem among cities. We take the urban region profiling as an application of smart cities and evaluate the proposed method with a real-world study. The experiments demonstrate the notable superiority of our framework over several competitive state-of-the-art methods.

Peng Xie, Minbo Ma, Bin Wang et al.

Accurate prediction of metro Origin-Destination (OD) flow is essential for the development of intelligent transportation systems and effective urban traffic management. Existing approaches typically either predict passenger outflow of departure stations or inflow of destination stations. However, we argue that travelers generally have clearly defined departure and arrival stations, making these OD pairs inherently interconnected. Consequently, considering OD pairs as a unified entity more accurately reflects actual metro travel patterns and allows for analyzing potential spatio-temporal correlations between different OD pairs. To address these challenges, we propose a novel and effective urban metro OD flow prediction method (UMOD), comprising three core modules: a data embedding module, a temporal relation module, and a spatial relation module. The data embedding module projects raw OD pair inputs into hidden space representations, which are subsequently processed by the temporal and spatial relation modules to capture both inter-pair and intra-pair spatio-temporal dependencies. Experimental results on two real-world urban metro OD flow datasets demonstrate that adopting the OD pairs perspective is critical for accurate metro OD flow prediction. Our method outperforms existing approaches, delivering superior predictive performance.

Zijian Zhang, Xiangyu Zhao, Hao Miao et al.

Spatio-Temporal prediction plays a critical role in smart city construction. Jointly modeling multiple spatio-temporal tasks can further promote an intelligent city life by integrating their inseparable relationship. However, existing studies fail to address this joint learning problem well, which generally solve tasks individually or a fixed task combination. The challenges lie in the tangled relation between different properties, the demand for supporting flexible combinations of tasks and the complex spatio-temporal dependency. To cope with the problems above, we propose an Automated Spatio-Temporal multi-task Learning (AutoSTL) method to handle multiple spatio-temporal tasks jointly. Firstly, we propose a scalable architecture consisting of advanced spatio-temporal operations to exploit the complicated dependency. Shared modules and feature fusion mechanism are incorporated to further capture the intrinsic relationship between tasks. Furthermore, our model automatically allocates the operations and fusion weight. Extensive experiments on benchmark datasets verified that our model achieves state-of-the-art performance. As we can know, AutoSTL is the first automated spatio-temporal multi-task learning method.

Songyu Ke, Ting Li, Li Song et al.

Accurate acquisition of crowd flow at Points of Interest (POIs) is pivotal for effective traffic management, public service, and urban planning. Despite this importance, due to the limitations of urban sensing techniques, the data quality from most sources is inadequate for monitoring crowd flow at each POI. This renders the inference of accurate crowd flow from low-quality data a critical and challenging task. The complexity is heightened by three key factors: 1) The scarcity and rarity of labeled data, 2) The intricate spatio-temporal dependencies among POIs, and 3) The myriad correlations between precise crowd flow and GPS reports. To address these challenges, we recast the crowd flow inference problem as a self-supervised attributed graph representation learning task and introduce a novel Contrastive Self-learning framework for Spatio-Temporal data (CSST). Our approach initiates with the construction of a spatial adjacency graph founded on the POIs and their respective distances. We then employ a contrastive learning technique to exploit large volumes of unlabeled spatio-temporal data. We adopt a swapped prediction approach to anticipate the representation of the target subgraph from similar instances. Following the pre-training phase, the model is fine-tuned with accurate crowd flow data. Our experiments, conducted on two real-world datasets, demonstrate that the CSST pre-trained on extensive noisy data consistently outperforms models trained from scratch.

Xingchen Zou, Yibo Yan, Xixuan Hao et al.

As cities continue to burgeon, Urban Computing emerges as a pivotal discipline for sustainable development by harnessing the power of cross-domain data fusion from diverse sources (e.g., geographical, traffic, social media, and environmental data) and modalities (e.g., spatio-temporal, visual, and textual modalities). Recently, we are witnessing a rising trend that utilizes various deep-learning methods to facilitate cross-domain data fusion in smart cities. To this end, we propose the first survey that systematically reviews the latest advancements in deep learning-based data fusion methods tailored for urban computing. Specifically, we first delve into data perspective to comprehend the role of each modality and data source. Secondly, we classify the methodology into four primary categories: feature-based, alignment-based, contrast-based, and generation-based fusion methods. Thirdly, we further categorize multi-modal urban applications into seven types: urban planning, transportation, economy, public safety, society, environment, and energy. Compared with previous surveys, we focus more on the synergy of deep learning methods with urban computing applications. Furthermore, we shed light on the interplay between Large Language Models (LLMs) and urban computing, postulating future research directions that could revolutionize the field. We firmly believe that the taxonomy, progress, and prospects delineated in our survey stand poised to significantly enrich the research community. The summary of the comprehensive and up-to-date paper list can be found at https://github.com/yoshall/Awesome-Multimodal-Urban-Computing.

Gang Li, Jizhong Liu, Heinrich Dinkel et al.

Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks. However, the audio modality has largely been overlooked in these developments. Thus, we conduct a series of RL explorations in audio understanding and reasoning, specifically focusing on the audio question answering (AQA) task. We leverage the group relative policy optimization (GRPO) algorithm to Qwen2-Audio-7B-Instruct, and our experiments demonstrated state-of-the-art performance on the MMAU Test-mini benchmark, achieving an accuracy rate of 64.5%. The main findings in this technical report are as follows: 1) The GRPO algorithm can be effectively applied to large audio language models (LALMs), even when the model has only 8.2B parameters; 2) With only 38k post-training samples, RL significantly outperforms supervised fine-tuning (SFT), indicating that RL-based approaches can be effective without large datasets; 3) The explicit reasoning process has not shown significant benefits for AQA tasks, and how to efficiently utilize deep thinking remains an open question for further research; 4) LALMs still lag far behind humans auditory-language reasoning, suggesting that the RL-based approaches warrant further exploration. Our project is available at https://github.com/xiaomi-research/r1-aqa and https://huggingface.co/mispeech/r1-aqa.

Heinrich Dinkel, Zhiyong Yan, Tianzi Wang et al.

Contrastive Language Audio Pretraining (CLAP) is a widely-used method to bridge the gap between audio and text domains. Current CLAP methods enable sound and music retrieval in English, ignoring multilingual spoken content. To address this, we introduce general language audio pretraining (GLAP), which expands CLAP with multilingual and multi-domain abilities. GLAP demonstrates its versatility by achieving competitive performance on standard audio-text retrieval benchmarks like Clotho and AudioCaps, while significantly surpassing existing methods in speech retrieval and classification tasks. Additionally, GLAP achieves strong results on widely used sound-event zero-shot benchmarks, while simultaneously outperforming previous methods on speech content benchmarks. Further keyword spotting evaluations across 50 languages emphasize GLAP's advanced multilingual capabilities. Finally, multilingual sound and music understanding is evaluated across four languages. Checkpoints and Source: https://github.com/xiaomi-research/dasheng-glap.

Qiongyan Wang, Yutong Xia, Siru ZHong et al.

Monitoring real-time air quality is essential for safeguarding public health and fostering social progress. However, the widespread deployment of air quality monitoring stations is constrained by their significant costs. To address this limitation, we introduce \emph{AirRadar}, a deep neural network designed to accurately infer real-time air quality in locations lacking monitoring stations by utilizing data from existing ones. By leveraging learnable mask tokens, AirRadar reconstructs air quality features in unmonitored regions. Specifically, it operates in two stages: first capturing spatial correlations and then adjusting for distribution shifts. We validate AirRadar's efficacy using a year-long dataset from 1,085 monitoring stations across China, demonstrating its superiority over multiple baselines, even with varying degrees of unobserved data. The source code can be accessed at https://github.com/CityMind-Lab/AirRadar.

Bin Wang, Yongqi Han, Minbo Ma et al.

Deep learning-based approaches have demonstrated significant advancements in time series forecasting. Despite these ongoing developments, the complex dynamics of time series make it challenging to establish the rule of thumb for designing the golden model architecture. In this study, we argue that refining existing advanced models through a universal calibrating strategy can deliver substantial benefits with minimal resource costs, as opposed to elaborating and training a new model from scratch. We first identify a multi-target learning conflict in the calibrating process, which arises when optimizing variables across time steps, leading to the underutilization of the model's learning capabilities. To address this issue, we propose an innovative calibrating strategy called Socket+Plug (SoP). This approach retains an exclusive optimizer and early-stopping monitor for each predicted target within each Plug while keeping the fully trained Socket backbone frozen. The model-agnostic nature of SoP allows it to directly calibrate the performance of any trained deep forecasting models, regardless of their specific architectures. Extensive experiments on various time series benchmarks and a spatio-temporal meteorological ERA5 dataset demonstrate the effectiveness of SoP, achieving up to a 22% improvement even when employing a simple MLP as the Plug (highlighted in Figure 1). Code is available at https://github.com/hanyuki23/SoP.

Hao Yu, Xin Yang, Xin Gao et al.

Personalized Federated Continual Learning (PFCL) is a new practical scenario that poses greater challenges in sharing and personalizing knowledge. PFCL not only relies on knowledge fusion for server aggregation at the global spatial-temporal perspective but also needs model improvement for each client according to the local requirements. Existing methods, whether in Personalized Federated Learning (PFL) or Federated Continual Learning (FCL), have overlooked the multi-granularity representation of knowledge, which can be utilized to overcome Spatial-Temporal Catastrophic Forgetting (STCF) and adopt generalized knowledge to itself by coarse-to-fine human cognitive mechanisms. Moreover, it allows more effectively to personalized shared knowledge, thus serving its own purpose. To this end, we propose a novel concept called multi-granularity prompt, i.e., coarse-grained global prompt acquired through the common model learning process, and fine-grained local prompt used to personalize the generalized representation. The former focuses on efficiently transferring shared global knowledge without spatial forgetting, and the latter emphasizes specific learning of personalized local knowledge to overcome temporal forgetting. In addition, we design a selective prompt fusion mechanism for aggregating knowledge of global prompts distilled from different clients. By the exclusive fusion of coarse-grained knowledge, we achieve the transmission and refinement of common knowledge among clients, further enhancing the performance of personalization. Extensive experiments demonstrate the effectiveness of the proposed method in addressing STCF as well as improving personalized performance. Our code now is available at https://github.com/SkyOfBeginning/FedMGP.

Zhiyong Yan, Heinrich Dinkel, Yongqing Wang et al.

Audio-text retrieval is a challenging task, requiring the search for an audio clip or a text caption within a database. The predominant focus of existing research on English descriptions poses a limitation on the applicability of such models, given the abundance of non-English content in real-world data. To address these linguistic disparities, we propose a language enhancement (LE), using a multilingual text encoder (SONAR) to encode the text data with language-specific information. Additionally, we optimize the audio encoder through the application of consistent ensemble distillation (CED), enhancing support for variable-length audio-text retrieval. Our methodology excels in English audio-text retrieval, demonstrating state-of-the-art (SOTA) performance on commonly used datasets such as AudioCaps and Clotho. Simultaneously, the approach exhibits proficiency in retrieving content in seven other languages with only 10% of additional language-enhanced training data, yielding promising results. The source code is publicly available https://github.com/zyyan4/ml-clap.

Xiyue Zhang, Chao Huang, Yong Xu et al.

Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment. While previous work has made significant efforts to learn traffic temporal dynamics and spatial dependencies, two key limitations exist in current models. First, only the neighboring spatial correlations among adjacent regions are considered in most existing methods, and the global inter-region dependency is ignored. Additionally, these methods fail to encode the complex traffic transition regularities exhibited with time-dependent and multi-resolution in nature. To tackle these challenges, we develop a new traffic prediction framework-Spatial-Temporal Graph Diffusion Network (ST-GDN). In particular, ST-GDN is a hierarchically structured graph neural architecture which learns not only the local region-wise geographical dependencies, but also the spatial semantics from a global perspective. Furthermore, a multi-scale attention network is developed to empower ST-GDN with the capability of capturing multi-level temporal dynamics. Experiments on several real-life traffic datasets demonstrate that ST-GDN outperforms different types of state-of-the-art baselines. Source codes of implementations are available at https://github.com/jill001/ST-GDN.

Junbo Zhang, Zhiwen Zhang, Yongqing Wang et al.

This paper introduces a new open-source speech corpus named "speechocean762" designed for pronunciation assessment use, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children. Five experts annotated each of the utterances at sentence-level, word-level and phoneme-level. A baseline system is released in open source to illustrate the phoneme-level pronunciation assessment workflow on this corpus. This corpus is allowed to be used freely for commercial and non-commercial purposes. It is available for free download from OpenSLR, and the corresponding baseline system is published in the Kaldi speech recognition toolkit.

Xin Yang, Hao Yu, Xin Gao et al.

Data privacy and silos are nontrivial and greatly challenging in many real-world applications. Federated learning is a decentralized approach to training models across multiple local clients without the exchange of raw data from client devices to global servers. However, existing works focus on a static data environment and ignore continual learning from streaming data with incremental tasks. Federated Continual Learning (FCL) is an emerging paradigm to address model learning in both federated and continual learning environments. The key objective of FCL is to fuse heterogeneous knowledge from different clients and retain knowledge of previous tasks while learning on new ones. In this work, we delineate federated learning and continual learning first and then discuss their integration, i.e., FCL, and particular FCL via knowledge fusion. In summary, our motivations are four-fold: we (1) raise a fundamental problem called ''spatial-temporal catastrophic forgetting'' and evaluate its impact on the performance using a well-known method called federated averaging (FedAvg), (2) integrate most of the existing FCL methods into two generic frameworks, namely synchronous FCL and asynchronous FCL, (3) categorize a large number of methods according to the mechanism involved in knowledge fusion, and finally (4) showcase an outlook on the future work of FCL.

Songyu Ke, Chenyu Wu, Yuxuan Liang et al.

Accurate acquisition of crowd flow at Points of Interest (POIs) is pivotal for effective traffic management, public service, and urban planning. Despite this importance, due to the limitations of urban sensing techniques, the data quality from most sources is inadequate for monitoring crowd flow at each POI. This renders the inference of accurate crowd flow from low-quality data a critical and challenging task. The complexity is heightened by three key factors: 1) \emph{The scarcity and rarity of labeled data}, 2) \emph{The intricate spatio-temporal dependencies among POIs}, and 3) \emph{The myriad correlations between precise crowd flow and GPS reports}. To address these challenges, we recast the crowd flow inference problem as a self-supervised attributed graph representation learning task and introduce a novel \underline{C}ontrastive \underline{S}elf-learning framework for \underline{S}patio-\underline{T}emporal data (\model). Our approach initiates with the construction of a spatial adjacency graph founded on the POIs and their respective distances. We then employ a contrastive learning technique to exploit large volumes of unlabeled spatio-temporal data. We adopt a swapped prediction approach to anticipate the representation of the target subgraph from similar instances. Following the pre-training phase, the model is fine-tuned with accurate crowd flow data. Our experiments, conducted on two real-world datasets, demonstrate that the \model pre-trained on extensive noisy data consistently outperforms models trained from scratch.

Jizhong Liu, Gang Li, Junbo Zhang et al.

Automated audio captioning (AAC) is an audio-to-text task to describe audio contents in natural language. Recently, the advancements in large language models (LLMs), with improvements in training approaches for audio encoders, have opened up possibilities for improving AAC. Thus, we explore enhancing AAC from three aspects: 1) a pre-trained audio encoder via consistent ensemble distillation (CED) is used to improve the effectivity of acoustic tokens, with a querying transformer (Q-Former) bridging the modality gap to LLM and compress acoustic tokens; 2) we investigate the advantages of using a Llama 2 with 7B parameters as the decoder; 3) another pre-trained LLM corrects text errors caused by insufficient training data and annotation ambiguities. Both the audio encoder and text decoder are optimized by low-rank adaptation (LoRA). Experiments show that each of these enhancements is effective. Our method obtains a 33.0 SPIDEr-FL score, outperforming the winner of DCASE 2023 Task 6A.

Minbo Ma, Peng Xie, Fei Teng et al.

Weather Forecasting is an attractive challengeable task due to its influence on human life and complexity in atmospheric motion. Supported by massive historical observed time series data, the task is suitable for data-driven approaches, especially deep neural networks. Recently, the Graph Neural Networks (GNNs) based methods have achieved excellent performance for spatio-temporal forecasting. However, the canonical GNNs-based methods only individually model the local graph of meteorological variables per station or the global graph of whole stations, lacking information interaction between meteorological variables in different stations. In this paper, we propose a novel Hierarchical Spatio-Temporal Graph Neural Network (HiSTGNN) to model cross-regional spatio-temporal correlations among meteorological variables in multiple stations. An adaptive graph learning layer and spatial graph convolution are employed to construct self-learning graph and study hidden dependency among nodes of variable-level and station-level graph. For capturing temporal pattern, the dilated inception as the backbone of gate temporal convolution is designed to model long and various meteorological trends. Moreover, a dynamic interaction learning is proposed to build bidirectional information passing in hierarchical graph. Experimental results on three real-world meteorological datasets demonstrate the superior performance of HiSTGNN beyond 7 baselines and it reduces the errors by 4.2% to 11.6% especially compared to state-of-the-art weather forecasting method.

Guoguo Chen, Shuzhou Chai, Guanbo Wang et al.

This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription. For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h. For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%. The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality. Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika.

Wei Huang, Tianrui Li, Dexian Wang et al.

In the federated learning setting, multiple clients jointly train a model under the coordination of the central server, while the training data is kept on the client to ensure privacy. Normally, inconsistent distribution of data across different devices in a federated network and limited communication bandwidth between end devices impose both statistical heterogeneity and expensive communication as major challenges for federated learning. This paper proposes an algorithm to achieve more fairness and accuracy in federated learning (FedFa). It introduces an optimization scheme that employs a double momentum gradient, thereby accelerating the convergence rate of the model. An appropriate weight selection algorithm that combines the information quantity of training accuracy and training frequency to measure the weights is proposed. This procedure assists in addressing the issue of unfairness in federated learning due to preferences for certain clients. Our results show that the proposed FedFa algorithm outperforms the baseline algorithm in terms of accuracy and fairness.

Guoguo Chen, Xingyu Na, Yongqing Wang et al.

This paper presents the "Ethiopian" system for the SLT 2021 Children Speech Recognition Challenge. Various data processing and augmentation techniques are proposed to tackle children's speech recognition problem, especially the lack of the children's speech recognition training data issue. Detailed experiments are designed and conducted to show the effectiveness of each technique, across different speech recognition toolkits and model architectures. Step by step, we explain how we come up with our final system, which provides the state-of-the-art results in the SLT 2021 Children Speech Recognition Challenge, with 21.66% CER on the Track 1 evaluation set (4th place overall), and 16.53% CER on the Track 2 evaluation set (1st place overall). Post-challenge analysis shows that our system actually achieves 18.82% CER on the Track 1 evaluation set, but we submitted the wrong version to the challenge organizer for Track 1.

Yuxuan Liang, Kun Ouyang, Yiwei Wang et al.

Citywide crowd flow analytics is of great importance to smart city efforts. It aims to model the crowd flow (e.g., inflow and outflow) of each region in a city based on historical observations. Nowadays, Convolutional Neural Networks (CNNs) have been widely adopted in raster-based crowd flow analytics by virtue of their capability in capturing spatial dependencies. After revisiting CNN-based methods for different analytics tasks, we expose two common critical drawbacks in the existing uses: 1) inefficiency in learning global spatial dependencies, and 2) overlooking latent region functions. To tackle these challenges, in this paper we present a novel framework entitled DeepLGR that can be easily generalized to address various citywide crowd flow analytics problems. This framework consists of three parts: 1) a local feature extraction module to learn representations for each region; 2) a global context module to extract global contextual priors and upsample them to generate the global features; and 3) a region-specific predictor based on tensor decomposition to provide customized predictions for each region, which is very parameter-efficient compared to previous methods. Extensive experiments on two typical crowd flow analytics tasks demonstrate the effectiveness, stability, and generality of our framework.

Yang Liu, Mingxin Chen, Wenxi Zhang et al.

It is commonly observed that the data are scattered everywhere and difficult to be centralized. The data privacy and security also become a sensitive topic. The laws and regulations such as the European Union's General Data Protection Regulation (GDPR) are designed to protect the public's data privacy. However, machine learning requires a large amount of data for better performance, and the current circumstances put deploying real-life AI applications in an extremely difficult situation. To tackle these challenges, in this paper we propose a novel privacy-preserving federated machine learning model, named Federated Extra-Trees, which applies local differential privacy in the federated trees model. A secure multi-institutional machine learning system was developed to provide superior performance by processing the modeling jointly on different clients without exchanging any raw data. We have validated the accuracy of our work by conducting extensive experiments on public datasets and the efficiency and robustness were also verified by simulating the real-world scenarios. Overall, we presented an extensible, scalable and practical solution to handle the data island problem.

Peng Xie, Tianrui Li, Jia Liu et al.

Urban spatial-temporal flows prediction is of great importance to traffic management, land use, public safety, etc. Urban flows are affected by several complex and dynamic factors, such as patterns of human activities, weather, events and holidays. Datasets evaluated the flows come from various sources in different domains, e.g. mobile phone data, taxi trajectories data, metro/bus swiping data, bike-sharing data and so on. To summarize these methodologies of urban flows prediction, in this paper, we first introduce four main factors affecting urban flows. Second, in order to further analysis urban flows, a preparation process of multi-sources spatial-temporal data related with urban flows is partitioned into three groups. Third, we choose the spatial-temporal dynamic data as a case study for the urban flows prediction task. Fourth, we analyze and compare some well-known and state-of-the-art flows prediction methods in detail, classifying them into five categories: statistics-based, traditional machine learning-based, deep learning-based, reinforcement learning-based and transfer learning-based methods. Finally, we give open challenges of urban flows prediction and an outlook in the future of this field. This paper will facilitate researchers find suitable methods and open datasets for addressing urban spatial-temporal flows forecast problems.

Huaishao Luo, Tianrui Li, Bing Liu et al.

This paper focuses on two related subtasks of aspect-based sentiment analysis, namely aspect term extraction and aspect sentiment classification, which we call aspect term-polarity co-extraction. The former task is to extract aspects of a product or service from an opinion document, and the latter is to identify the polarity expressed in the document about these extracted aspects. Most existing algorithms address them as two separate tasks and solve them one by one, or only perform one task, which can be complicated for real applications. In this paper, we treat these two tasks as two sequence labeling problems and propose a novel Dual crOss-sharEd RNN framework (DOER) to generate all aspect term-polarity pairs of the input sentence simultaneously. Specifically, DOER involves a dual recurrent neural network to extract the respective representation of each task, and a cross-shared unit to consider the relationship between them. Experimental results demonstrate that the proposed framework outperforms state-of-the-art baselines on three benchmark datasets.

Yang Liu, Yingting Liu, Zhijie Liu et al.

Most real-world data are scattered across different companies or government organizations, and cannot be easily integrated under data privacy and related regulations such as the European Union's General Data Protection Regulation (GDPR) and China' Cyber Security Law. Such data islands situation and data privacy & security are two major challenges for applications of artificial intelligence. In this paper, we tackle these challenges and propose a privacy-preserving machine learning model, called Federated Forest, which is a lossless learning model of the traditional random forest method, i.e., achieving the same level of accuracy as the non-privacy-preserving approach. Based on it, we developed a secure cross-regional machine learning system that allows a learning process to be jointly trained over different regions' clients with the same user samples but different attribute sets, processing the data stored in each of them without exchanging their raw data. A novel prediction algorithm was also proposed which could largely reduce the communication overhead. Experiments on both real-world and UCI data sets demonstrate the performance of the Federated Forest is as accurate as the non-federated version. The efficiency and robustness of our proposed system had been verified. Overall, our model is practical, scalable and extensible for real-life tasks.

Yuxuan Liang, Kun Ouyang, Lin Jing et al.

Urban flow monitoring systems play important roles in smart city efforts around the world. However, the ubiquitous deployment of monitoring devices, such as CCTVs, induces a long-lasting and enormous cost for maintenance and operation. This suggests the need for a technology that can reduce the number of deployed devices, while preventing the degeneration of data accuracy and granularity. In this paper, we aim to infer the real-time and fine-grained crowd flows throughout a city based on coarse-grained observations. This task is challenging due to two reasons: the spatial correlations between coarse- and fine-grained urban flows, and the complexities of external impacts. To tackle these issues, we develop a method entitled UrbanFM based on deep neural networks. Our model consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs by using a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influences of different external factors. Extensive experiments on two real-world datasets, namely TaxiBJ and HappyValley, validate the effectiveness and efficiency of our method compared to seven baselines, demonstrating the state-of-the-art performance of our approach on the fine-grained urban flow inference problem.

Haitong Zhang, Junbo Zhang, Yujun Wang

In this paper, we propose an attention-based end-to-end model for multi-channel keyword spotting (KWS), which is trained to optimize the KWS result directly. As a result, our model outperforms the baseline model with signal pre-processing techniques in both the clean and noisy testing data. We also found that multi-task learning results in a better performance when the training and testing data are similar. Transfer learning and multi-target spectral mapping can dramatically enhance the robustness to the noisy environment. At 0.1 false alarm (FA) per hour, the model with transfer learning and multi-target mapping gain an absolute 30% improvement in the wake-up rate in the noisy data with SNR about -20.

Haitong Zhang, Junbo Zhang, Yujun Wang

In this paper, we propose a sequence-to-sequence model for keyword spotting (KWS). Compared with other end-to-end architectures for KWS, our model simplifies the pipelines of production-quality KWS system and satisfies the requirement of high accuracy, low-latency, and small-footprint. We also evaluate the performances of different encoder architectures, which include LSTM and GRU. Experiments on the real-world wake-up data show that our approach outperforms the recently proposed attention-based end-to-end model. Specifically speaking, with 73K parameters, our sequence-to-sequence model achieves $\sim$3.05\% false rejection rate (FRR) at 0.1 false alarm (FA) per hour.

Zheyi Pan, Yuxuan Liang, Junbo Zhang et al.

Spatio-temporal (ST) data, which represent multiple time series data corresponding to different spatial locations, are ubiquitous in real-world dynamic systems, such as air quality readings. Forecasting over ST data is of great importance but challenging as it is affected by many complex factors, including spatial characteristics, temporal characteristics and the intrinsic causality between them. In this paper, we propose a general framework (HyperST-Net) based on hypernetworks for deep ST models. More specifically, it consists of three major modules: a spatial module, a temporal module and a deduction module. Among them, the deduction module derives the parameter weights of the temporal module from the spatial characteristics, which are extracted by the spatial module. Then, we design a general form of HyperST layer as well as different forms for several basic layers in neural networks, including the dense layer (HyperST-Dense) and the convolutional layer (HyperST-Conv). Experiments on three types of real-world tasks demonstrate that the predictive models integrated with our framework achieve significant improvements, and outperform the state-of-the-art baselines as well.

Changhao Shan, Junbo Zhang, Yujun Wang et al.

In this paper, we propose an attention-based end-to-end neural approach for small-footprint keyword spotting (KWS), which aims to simplify the pipelines of building a production-quality KWS system. Our model consists of an encoder and an attention mechanism. The encoder transforms the input signal into a high level representation using RNNs. Then the attention mechanism weights the encoder features and generates a fixed-length vector. Finally, by linear transformation and softmax function, the vector becomes a score used for keyword detection. We also evaluate the performance of different encoder architectures, including LSTM, GRU and CRNN. Experiments on real-world wake-up data show that our approach outperforms the recent Deep KWS approach by a large margin and the best performance is achieved by CRNN. To be more specific, with ~84K parameters, our attention-based model achieves 1.02% false rejection rate (FRR) at 1.0 false alarm (FA) per hour.

Ke Wang, Junbo Zhang, Yujun Wang et al.

Speaker adaptation aims to estimate a speaker specific acoustic model from a speaker independent one to minimize the mismatch between the training and testing conditions arisen from speaker variabilities. A variety of neural network adaptation methods have been proposed since deep learning models have become the main stream. But there still lacks an experimental comparison between different methods, especially when DNN-based acoustic models have been advanced greatly. In this paper, we aim to close this gap by providing an empirical evaluation of three typical speaker adaptation methods: LIN, LHUC and KLD. Adaptation experiments, with different size of adaptation data, are conducted on a strong TDNN-LSTM acoustic model. More challengingly, here, the source and target we are concerned with are standard Mandarin speaker model and accented Mandarin speaker model. We compare the performances of different methods and their combinations. Speaker adaptation performance is also examined by speaker's accent degree.

Ke Wang, Junbo Zhang, Sining Sun et al.

We investigate the use of generative adversarial networks (GANs) in speech dereverberation for robust speech recognition. GANs have been recently studied for speech enhancement to remove additive noises, but there still lacks of a work to examine their ability in speech dereverberation and the advantages of using GANs have not been fully established. In this paper, we provide deep investigations in the use of GAN-based dereverberation front-end in ASR. First, we study the effectiveness of different dereverberation networks (the generator in GAN) and find that LSTM leads a significant improvement as compared with feed-forward DNN and CNN in our dataset. Second, further adding residual connections in the deep LSTMs can boost the performance as well. Finally, we find that, for the success of GAN, it is important to update the generator and the discriminator using the same mini-batch data during training. Moreover, using reverberant spectrogram as a condition to discriminator, as suggested in previous studies, may degrade the performance. In summary, our GAN-based dereverberation front-end achieves 14%-19% relative CER reduction as compared to the baseline DNN dereverberation network when tested on a strong multi-condition training acoustic model.

Changhao Shan, Junbo Zhang, Yujun Wang et al.

Recently, there has been a growing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. In this paper, we explore the use of attention-based encoder-decoder model for Mandarin speech recognition on a voice search task. Previous attempts have shown that applying attention-based encoder-decoder to Mandarin speech recognition was quite difficult due to the logographic orthography of Mandarin, the large vocabulary and the conditional dependency of the attention model. In this paper, we use character embedding to deal with the large vocabulary. Several tricks are used for effective model training, including L2 regularization, Gaussian weight noise and frame skipping. We compare two attention mechanisms and use attention smoothing to cover long context in the attention model. Taken together, these tricks allow us to finally achieve a character error rate (CER) of 3.58% and a sentence error rate (SER) of 7.43% on the MiTV voice search dataset. While together with a trigram language model, CER and SER reach 2.81% and 5.77%, respectively.

Junbo Zhang, Yu Zheng, Dekang Qi et al.

Forecasting the flow of crowds is of great importance to traffic management and public safety, and very challenging as it is affected by many complex factors, including spatial dependencies (nearby and distant), temporal dependencies (closeness, period, trend), and external conditions (e.g., weather and events). We propose a deep-learning-based approach, called ST-ResNet, to collectively forecast two types of crowd flows (i.e. inflow and outflow) in each and every region of a city. We design an end-to-end structure of ST-ResNet based on unique properties of spatio-temporal data. More specifically, we employ the residual neural network framework to model the temporal closeness, period, and trend properties of crowd traffic. For each property, we design a branch of residual convolutional units, each of which models the spatial properties of crowd traffic. ST-ResNet learns to dynamically aggregate the output of the three residual neural networks based on data, assigning different weights to different branches and regions. The aggregation is further combined with external factors, such as weather and day of the week, to predict the final traffic of crowds in each and every region. We have developed a real-time system based on Microsoft Azure Cloud, called UrbanFlow, providing the crowd flow monitoring and forecasting in Guiyang City of China. In addition, we present an extensive experimental evaluation using two types of crowd flows in Beijing and New York City (NYC), where ST-ResNet outperforms nine well-known baselines.

Junbo Zhang, Tianrui Li, Yi Pan

The rapid growth of emerging information technologies and application patterns in modern society, e.g., Internet, Internet of Things, Cloud Computing and Tri-network Convergence, has caused the advent of the era of big data. Big data contains huge values, however, mining knowledge from big data is a tremendously challenging task because of data uncertainty and inconsistency. Attribute reduction (also known as feature selection) can not only be used as an effective preprocessing step, but also exploits the data redundancy to reduce the uncertainty. However, existing solutions are designed 1) either for a single machine that means the entire data must fit in the main memory and the parallelism is limited; 2) or for the Hadoop platform which means that the data have to be loaded into the distributed memory frequently and therefore become inefficient. In this paper, we overcome these shortcomings for maximum efficiency possible, and propose a unified framework for Parallel Large-scale Attribute Reduction, termed PLAR, for big data analysis. PLAR consists of three components: 1) Granular Computing (GrC)-based initialization: it converts a decision table (i.e., original data representation) into a granularity representation which reduces the amount of space and hence can be easily cached in the distributed memory: 2) model-parallelism: it simultaneously evaluates all feature candidates and makes attribute reduction highly parallelizable; 3) data-parallelism: it computes the significance of an attribute in parallel using a MapReduce-style manner. We implement PLAR with four representative heuristic feature selection algorithms on Spark, and evaluate them on various huge datasets, including UCI and astronomical datasets, finding our method's advantages beyond existing solutions.

Junbo Zhang, Yu Zheng, Dekang Qi

Forecasting the flow of crowds is of great importance to traffic management and public safety, yet a very challenging task affected by many complex factors, such as inter-region traffic, events and weather. In this paper, we propose a deep-learning-based approach, called ST-ResNet, to collectively forecast the in-flow and out-flow of crowds in each and every region through a city. We design an end-to-end structure of ST-ResNet based on unique properties of spatio-temporal data. More specifically, we employ the framework of the residual neural networks to model the temporal closeness, period, and trend properties of the crowd traffic, respectively. For each property, we design a branch of residual convolutional units, each of which models the spatial properties of the crowd traffic. ST-ResNet learns to dynamically aggregate the output of the three residual neural networks based on data, assigning different weights to different branches and regions. The aggregation is further combined with external factors, such as weather and day of the week, to predict the final traffic of crowds in each and every region. We evaluate ST-ResNet based on two types of crowd flows in Beijing and NYC, finding that its performance exceeds six well-know methods.