One global model in federated learning (FL) might not be sufficient to serve many clients with non-IID tasks and distributions. Despite recent advances in FL to train multiple global models for better personalization, they only provide limited model choices to clients, so local finetuning of multiple models is still indispensable. This paper proposes a novel ``FedMerge'' approach that can create a single personalized model per client by simply merging multiple global models with automatically optimized and customized weights. We formulate this problem as a joint optimization of global models and the merging weights per client. Unlike existing FL approaches, where the server broadcasts one or multiple global models to all clients, the server only needs to send a customized, merged model to each client. Moreover, instead of periodically interrupting the local training and re-initializing it to a global model, the merged model aligns better with each client's task and data distribution, smoothening the local-global gap between consecutive rounds caused by client drift. We evaluate FedMerge on different non-IID settings applied to various domains with diverse tasks and data types, in which FedMerge consistently outperforms existing FL approaches, including clustering-based and mixture-of-experts (MoE) based methods.

Federated foundation models represent a new paradigm to jointly fine-tune pre-trained foundation models across clients. It is still a challenge to fine-tune foundation models for a small group of new users or specialized scenarios, which typically involve limited data compared to the large-scale data used in pre-training. In this context, the trade-off between personalization and federation becomes more sensitive. To tackle these, we proposed a bi-level personalization framework for federated fine-tuning on foundation models. Specifically, we conduct personalized fine-tuning on the client-level using its private data, and then conduct a personalized aggregation on the server-level using similar users measured by client-specific task vectors. Given the personalization information gained from client-level fine-tuning, the server-level personalized aggregation can gain group-wise personalization information while mitigating the disturbance of irrelevant or interest-conflict clients with non-IID data. The effectiveness of the proposed algorithm has been demonstrated by extensive experimental analysis in benchmark datasets.

User-centric recommendation has become essential for delivering personalized services, as it enables systems to adapt to users' evolving behaviors while respecting their long-term preferences and privacy constraints. Although federated learning offers a promising alternative to centralized training, existing approaches largely overlook user behavior dynamics, leading to temporal forgetting and weakened collaborative personalization. In this work, we propose FCUCR, a federated continual recommendation framework designed to support long-term personalization in a privacy-preserving manner. To address temporal forgetting, we introduce a time-aware self-distillation strategy that implicitly retains historical preferences during local model updates. To tackle collaborative personalization under heterogeneous user data, we design an inter-user prototype transfer mechanism that enriches each client's representation using knowledge from similar users while preserving individual decision logic. Extensive experiments on four public benchmarks demonstrate the superior effectiveness of our approach, along with strong compatibility and practical applicability. Code is available at https://github.com/Poizoner/code4FCUCR_www2026.

Federated Recommendation (FR) has emerged as a promising paradigm for addressing the learn-to-rank problem in a privacy-preserving manner. However, effectively incorporating multimodal item features into FR remains an open challenge, due to efficiency constraints, distribution heterogeneity, and feature utilization alignment with the recommendation objective. To tackle these issues, we propose GFMFR, a novel multimodal fusion framework for federated recommendation. Specifically, multimodal representation learning is offloaded to the server, which stores item content and employs a high-capacity encoder to generate expressive representations, thereby alleviating the computational burden on clients. In addition, a group-aware multimodal aggregation mechanism learns shared representations for users with similar interests, enabling knowledge sharing while alleviating distribution heterogeneity. Finally, GFMFR adopts a preference-guided distillation strategy that leverages multimodal information in a way directly aligned with recommendation objectives. The proposed framework can be seamlessly integrated into existing federated recommender systems, enhancing their effectiveness by incorporating multimodal features. Extensive experiments on five benchmark datasets demonstrate that GFMFR consistently outperforms state-of-the-art multimodal FR baselines. The implementation code is available. https://github.com/Zhangwp2420/GFMFR.

Training a general-purpose time series foundation models with robust generalization capabilities across diverse applications from scratch is still an open challenge. Efforts are primarily focused on fusing cross-domain time series datasets to extract shared subsequences as tokens for training models on Transformer architecture. However, due to significant statistical heterogeneity across domains, this cross-domain fusing approach doesn't work effectively as the same as fusing texts and images. To tackle this challenge, this paper proposes a novel federated learning approach to address the heterogeneity in time series foundation models training, namely FFTS. Specifically, each data-holding organization is treated as an independent client in a collaborative learning framework with federated settings, and then many client-specific local models will be trained to preserve the unique characteristics per dataset. Moreover, a new regularization mechanism will be applied to both client-side and server-side, thus to align the shared knowledge across heterogeneous datasets from different domains. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed federated learning approach. The newly learned time series foundation models achieve superior generalization capabilities on cross-domain time series analysis tasks, including forecasting, imputation, and anomaly detection.

Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy in a federated setting. Existing FedCF methods typically combine distributed Collaborative Filtering (CF) algorithms with privacy-preserving mechanisms, and then preserve personalized information into a user embedding vector. However, the user embedding is usually insufficient to preserve the rich information of the fine-grained personalization across heterogeneous clients. This paper proposes a novel personalized FedCF method by preserving users' personalized information into a latent variable and a neural model simultaneously. Specifically, we decompose the modeling of user knowledge into two encoders, each designed to capture shared knowledge and personalized knowledge separately. A personalized gating network is then applied to balance personalization and generalization between the global and local encoders. Moreover, to effectively train the proposed framework, we model the CF problem as a specialized Variational AutoEncoder (VAE) task by integrating user interaction vector reconstruction with missing value prediction. The decoder is trained to reconstruct the implicit feedback from items the user has interacted with, while also predicting items the user might be interested in but has not yet interacted with. Experimental results on benchmark datasets demonstrate that the proposed method outperforms other baseline methods, showcasing superior performance.

Multifaceted user modeling aims to uncover fine-grained patterns and learn representations from user data, revealing their diverse interests and characteristics, such as profile, preference, and personality. Recent studies on foundation model-based recommendation have emphasized the Transformer architecture's remarkable ability to capture complex, non-linear user-item interaction relationships. This paper aims to advance foundation model-based recommendersystems by introducing enhancements to multifaceted user modeling capabilities. We propose a novel Transformer layer designed specifically for recommendation, using the self-attention mechanism to capture sequential user-item interaction patterns. Specifically, we design a group gating network to identify user groups, enabling hierarchical discovery across different layers, thereby capturing the multifaceted nature of user interests through multiple Transformer layers. Furthermore, to broaden the data scope and further enhance multifaceted user modeling, we extend the framework to a federated setting, enabling the use of private datasets while ensuring privacy. Experimental validations on benchmark datasets demonstrate the superior performance of our proposed method.

The Base-New Trade-off (BNT) problem universally exists during the optimization of CLIP-based prompt tuning, where continuous fine-tuning on base (target) classes leads to a simultaneous decrease of generalization ability on new (unseen) classes. Existing approaches attempt to regulate the prompt tuning process to balance BNT by appending constraints. However, imposed on the same target prompt, these constraints fail to fully avert the mutual exclusivity between the optimization directions for base and new. As a novel solution to this challenge, we propose the plug-andplay Dual-Prompt Collaboration (DPC) framework, the first that decoupling the optimization processes of base and new tasks at the prompt level. Specifically, we clone a learnable parallel prompt based on the backbone prompt, and introduce a variable Weighting-Decoupling framework to independently control the optimization directions of dual prompts specific to base or new tasks, thus avoiding the conflict in generalization. Meanwhile, we propose a Dynamic Hard Negative Optimizer, utilizing dual prompts to construct a more challenging optimization task on base classes for enhancement. For interpretability, we prove the feature channel invariance of the prompt vector during the optimization process, providing theoretical support for the Weighting-Decoupling of DPC. Extensive experiments on multiple backbones demonstrate that DPC can significantly improve base performance without introducing any external knowledge beyond the base classes, while maintaining generalization to new classes. Code is available at: https://github.com/JREion/DPC.

Though CLIP-based prompt tuning significantly enhances pre-trained Vision-Language Models, existing research focuses on reconstructing the model architecture, e.g., additional loss calculation and meta-networks. These approaches generally lead to increased complexity and extended training cost. To maintain the efficiency of the tuning process, we propose plug-and-play Model-Agnostic Optimization (MAO) for prompt tuning. Without altering any components of the prompt tuning backbone, we introduce a Data-Driven Enhancement framework to optimize the distribution of the initial data, and incorporate an Alterable Regularization module to boost the task-specific feature processing pipeline, thereby improving overall performance while maintaining low computational cost. Extensive experiments on MAO demonstrate its outstanding performance and efficiency.

Clustered Federated Learning (CFL) addresses the challenges posed by non-IID data by training multiple group- or cluster-specific expert models. However, existing methods often overlook the shared information across clusters, which represents the generalizable knowledge valuable to all participants in the Federated Learning (FL) system. To overcome this limitation, this paper introduces a novel FL framework that distills a universal expert model from the knowledge of multiple clusters. This universal expert captures globally shared information across all clients and is subsequently distributed to each client as the initialization for the next round of model training. The proposed FL framework operates in three iterative steps: (1) local model training at each client, (2) cluster-specific model aggregation, and (3) universal expert distillation. This three-step learning paradigm ensures the preservation of fine-grained non-IID characteristics while effectively incorporating shared knowledge across clusters. Compared to traditional gradient-based aggregation methods, the distillation-based model aggregation introduces greater flexibility in handling model heterogeneity and reduces conflicts among cluster-specific experts. Extensive experimental results demonstrate the superior performance of the proposed method across various scenarios, highlighting its potential to advance the state of CFL by balancing personalized and shared knowledge more effectively.

Effectively leveraging private datasets remains a significant challenge in developing foundation models. Federated Learning (FL) has recently emerged as a collaborative framework that enables multiple users to fine-tune these models while mitigating data privacy risks. Meanwhile, Low-Rank Adaptation (LoRA) offers a resource-efficient alternative for fine-tuning foundation models by dramatically reducing the number of trainable parameters. This survey examines how LoRA has been integrated into federated fine-tuning for foundation models—an area we term FedLoRA—by focusing on three key challenges: distributed learning, heterogeneity, and efficiency. We further categorize existing work based on the specific methods used to address each challenge. Finally, we discuss open research questions and highlight promising directions for future investigation, outlining the next steps for advancing FedLoRA.

Representation learning on electronic health records (EHRs) plays a vital role in downstream medical prediction tasks. Although natural language processing techniques, such as recurrent neural networks, and self-attention, have been adapted for learning medical representations from hierarchical, time-stamped EHR data, they often struggle when either general or task-specific data are limited. Recent efforts have attempted to mitigate this challenge by incorporating medical ontologies (i.e., knowledge graphs) into self-supervised tasks like diagnosis prediction. However, two main issues remain: (1) small and uniform ontologies that lack diversity for robust learning, and (2) insufficient attention to the critical contexts or dependencies underlying patient journeys, which could further enhance ontology-based learning. To address these gaps, we propose MIPO (Mutual Integration of Patient Journey and Medical Ontology), a robust end-to-end framework that employs a Transformer-based architecture for representation learning. MIPO emphasizes task-specific representation learning through a sequential diagnosis prediction task, while also incorporating an ontology-based disease-typing task. A graph-embedding module is introduced to integrate information from patient visit records, thus alleviating data insufficiency. This setup creates a mutually reinforcing loop, where both patient-journey embedding and ontology embedding benefit from each other. We validate MIPO on two real-world benchmark datasets, showing that it consistently outperforms baseline methods under both sufficient and limited data conditions. Furthermore, the resulting diagnosis embeddings offer improved interpretability, underscoring the promise of MIPO for real-world healthcare applications.

Recently, frequency transformation (FT) has been increasingly incorporated into deep learning models to significantly enhance state-of-the-art accuracy and efficiency in time series analysis. The advantages of FT, such as high efficiency and a global view, have been rapidly explored and exploited in various time series tasks and applications, demonstrating the promising potential of FT as a new deep learning paradigm for time series analysis. Despite the growing attention and the proliferation of research in this emerging field, there is currently a lack of a systematic review and in-depth analysis of deep learning-based time series models with FT. It is also unclear why FT can enhance time series analysis and what its limitations are in the field. To address these gaps, we present a comprehensive review that systematically investigates and summarizes the recent research advancements in deep learning-based time series analysis with FT. Specifically, we explore the primary approaches used in current models that incorporate FT, the types of neural networks that leverage FT, and the representative FT-equipped models in deep time series analysis. We propose a novel taxonomy to categorize the existing methods in this field, providing a structured overview of the diverse approaches employed in incorporating FT into deep learning models for time series analysis. Finally, we highlight the advantages and limitations of FT for time series modeling and identify potential future research directions that can further contribute to the community of time series analysis.

Heterogeneous Federated Learning (HtFL) enables collaborative learning across clients with diverse model architectures and non-IID data distributions, which are prevalent in real-world edge computing applications. Existing HtFL approaches typically employ proxy datasets to facilitate knowledge sharing or implement coarse-grained model-level knowledge transfer. However, such approaches not only elevate risks of user privacy leakage but also lead to the loss of fine-grained model-specific knowledge, ultimately creating barriers to effective knowledge sharing. To address these challenges, we propose FedFree, a novel data-free and model-free HtFL framework featuring two key innovations. First, FedFree introduces a reverse layer-wise knowledge transfer mechanism that aggregates heterogeneous client models into a global model solely using Gaussian-based pseudo data, eliminating reliance on proxy datasets. Second, it leverages Knowledge Gain Entropy (KGE) to guide targeted layer-wise knowledge alignment, ensuring that each client receives the most relevant global updates tailored to its specific architecture. We provide rigorous theoretical convergence guarantees for FedFree and conduct extensive experiments on CIFAR-10 and CIFAR-100. Results demonstrate that FedFree achieves substantial performance gains, with relative accuracy improving up to 46.3% over state-of-the-art baselines. The framework consistently excels under highly heterogeneous model/data distributions and in large scale settings.

Can we build accurate world models out of large language models (LLMs)? How can world models benefit LLM agents? The gap between the prior knowledge of LLMs and the specified environment's dynamics usually bottlenecks LLMs' performance as world models. To bridge the gap, we propose a training-free "world alignment" that learns an environment's symbolic knowledge complementary to LLMs. The symbolic knowledge covers action rules, knowledge graphs, and scene graphs, which are extracted by LLMs from exploration trajectories and encoded into executable codes to regulate LLM agents' policies. We further propose an RL-free, model-based agent "WALL-E" through the model-predictive control (MPC) framework. Unlike classical MPC requiring costly optimization on the fly, we adopt an LLM agent as an efficient look-ahead optimizer of future steps' actions by interacting with the neurosymbolic world model. While the LLM agent's strong heuristics make it an efficient planner in MPC, the quality of its planned actions is also secured by the accurate predictions of the aligned world model. They together considerably improve learning efficiency in a new environment. On open-world challenges in Mars (Minecraft like) and ALFWorld (embodied indoor environments), WALL-E significantly outperforms existing methods, e.g., surpassing baselines in Mars by 16.1%–51.6% of success rate and by at least 61.7% in score. In ALFWorld, it achieves a new record 98% success rate after only 4 iterations.

In China, the number of riders in the on-demand delivery industry has surpassed ten million. Ensuring that these riders earn a decent income can enhance their financial security, reduce poverty, and promote social equity and stability. Due to ease of use, lower-cost maintenance and environmental friendliness, electric bicycles (e-bikes) are the primary mode of transportation for delivery riders. However, these riders frequently encounter depleted batteries due to limited capacity and prolonged charging times, necessitating inconvenient swaps or recharges during deliveries. To address this issue, we propose the e-bike Battery Swap-as-a-Service (eBaaS), an innovative battery-swapping system that leverages an intelligent AIoT network for seamless battery swapping at distributed locations across urban areas. eBaaS integrates edge-cloud collaboration, battery resource allocation, battery anomaly detection, and battery range prediction to minimize downtime and reduce unnecessary mileage. While eBaaS's potential benefits are evident, there has been a lack of robust methods to quantify its impact. Thus, we further developed the eBaaS Impact Evaluation Method (EIEM), the first comprehensive model to address this gap. EIEM analyzes data from approximately 260,000 delivery riders and 5 million riding trajectories. Findings indicate that eBaaS reduces average invalid mileage by 6 km and increases the order volume by an average of over 20% daily per e-bike rider. Meanwhile, the annual electricity savings result in a reduction of 2.74 million kilograms of carbon emissions for 260,000 riders. The eBaaS system is therefore significantly beneficial for environmental conservation and sustainable urban development.

Traffic forecasting plays a crucial role in establishing an Intelligent Transportation System (ITS) by providing essential insights. Existing traffic forecasting relies on the assumption that there is a hidden invariant spatial-temporal pattern in the large-scale dataset. However, the traffic patterns are easily influenced by many unpredictable external factors, such as policy interventions and climate changes. Due to the dynamic nature of these exogenous factors, the traffic network's spatial-temporal patterns are also changed, thus impacting the performance of traffic forecasting models. Thus, there is an urgent need to rethink the traffic forecasting model in a fast-adaptive manner. To solve this challenge, this paper proposes an Adaptive Spatio-Temporal Context Learning framework named ASTCL, which achieves desired forecasting accuracy using daily basis traffic data collected from dozens of sensors. ASTCL constructs adaptive spatio-temporal contexts for target locations in the traffic network and generates dynamic sequence graphs based on semantic similarities. The adaptive contexts aggregate valuable information from available data, while the graphs reveal dynamic trends in traffic properties. Further, ASTCL introduces a joint convolution and attention mechanism to model intricate spatio-temporal relationships from multiple perspectives. Extensive experiments conducted on four real-world datasets demonstrate that ASTCL achieves remarkable fast adaptability and outperforms other state-of-the-art methods by a significant margin.

Federated recommender systems (FedRecSys) have emerged as a pivotal solution for privacy-aware recommendations, balancing growing demands for data security and personalized experiences. Current research efforts predominantly concentrate on adapting traditional recommendation architectures to federated environments, optimizing communication efficiency, and mitigating security vulnerabilities. However, user personalization modeling, which is essential for capturing heterogeneous preferences in this decentralized and non-IID data setting, remains underexplored. This survey addresses this gap by systematically exploring personalization in FedRecSys, charting its evolution from centralized paradigms to federated-specific innovations. We establish a foundational definition of personalization in a federated setting, emphasizing personalized models as a critical solution for capturing fine-grained user preferences. The work critically examines the technical hurdles of building personalized FedRecSys and synthesizes promising methodologies to meet these challenges. As the first consolidated study in this domain, this survey serves as both a technical reference and a catalyst for advancing personalized FedRecSys research.

Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder. However, in contrast to passages or sentences, retrieval on long documents suffers from the \textit{scope hypothesis} that a long document may cover multiple topics. This maximizes their structure heterogeneity and poses a granular-mismatch issue, leading to an inferior distillation efficacy. In this work, we propose a new learning framework, fine-grained distillation (FGD), for long-document retrievers. While preserving the conventional dense retrieval paradigm, it first produces global-consistent representations crossing different fine granularity and then applies multi-granular aligned distillation merely during training. In experiments, we evaluate our framework on two long-document retrieval benchmarks, which show state-of-the-art performance.

Jiazhan Feng, Chongyang Tao, Xiubo Geng, Tao Shen, Can Xu, Guodong Long, Dongyan Zhao, Daxin Jiang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Recent large-scale vision-language pre-training depends on image-text global alignment by contrastive learning and is further boosted by fine-grained alignment in a weakly contrastive manner for cross-modal retrieval. Nonetheless, besides semantic matching learned by contrastive learning, cross-modal retrieval also largely relies on object matching between modalities. This necessitates fine-grained categorical discriminative learning, which however suffers from scarce data in full-supervised scenarios and information asymmetry in weakly-supervised scenarios when applied to cross-modal retrieval. To address these issues, we propose expansive lexicon-patch alignment (ELA) to align image patches with a vocabulary rather than only the words explicitly in the text for annotation-free alignment and information augmentation, thus enabling more effective fine-grained categorical discriminative learning for cross-modal retrieval. Experimental results show that ELA could effectively learn representative fine-grained information and outperform state-of-the-art methods on cross-modal retrieval.

Yang Li, Canran Xu, Guodong Long, Tao Shen, Chongyang Tao, Jing Jiang. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

To enhance the reasoning capabilities of offthe-shelf Large Language Models (LLMs), we introduce a simple, yet general and effective prompting method, RE2, i.e., Re-Reading the question as input.Unlike most thoughteliciting prompting methods, such as Chain-of-Thought (CoT), which aim to elicit the reasoning process in the output, RE2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process.Consequently, RE2 demonstrates strong generality and compatibility with most thoughteliciting prompting methods, including CoT.Crucially, RE2 facilitates a "bidirectional" encoding in unidirectional decoder-only LLMs because the first pass could provide global information for the second pass.We begin with a preliminary empirical study as the foundation of RE2, illustrating its potential to enable "bidirectional" attention mechanisms.We then evaluate RE2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality.Our findings indicate that, with the exception of a few scenarios on vanilla ChatGPT, RE2 consistently enhances the reasoning performance of LLMs through a simple re-reading strategy.Further analyses reveal RE2's adaptability, showing how it can be effectively integrated with different LLMs, thought-eliciting prompting, and ensemble strategies. 1

Building recommendation systems via federated learning (FL) is a new emerging challenge for next-generation Internet service. Existing FL models share item embedding across clients while keeping the user embedding private and local on the client side. However, identical item embedding cannot capture users' individual differences in perceiving the same item and may lead to poor personalization. Moreover, dense item embedding in FL results in expensive communication costs and latency. To address these challenges, we propose Federated Recommendation withAdditive Personalization (FedRAP), which learns a global view of items via FL and a personalized view locally on each user. FedRAP encourages a sparse global view to save FL's communication cost and enforces the two views to be complementary via two regularizers. We propose an effective curriculum to learn the local and global views progressively with increasing regularization weights. To produce recommendations for a user, FedRAP adds the two views together to obtain a personalized item embedding. FedRAP achieves the best performance in FL setting on multiple benchmarks. It outperforms recent federated recommendation methods and several ablation study baselines. Our code is available at https://github.com/mtics/FedRAP.

Personalized Federated Learning (PerFL) is a new machine learning paradigm that delivers personalized models for diverse clients under federated learning settings. Most PerFL methods require extra learning processes on a client to adapt a globally shared model to the client-specific personalized model using its own local data. However, the model adaptation process in PerFL is still an open challenge in the stage of model deployment and test time. This work tackles the challenge by proposing a novel federated learning framework to learn only one robust global model to achieve competitive performance to those personalized models on unseen/test clients in the FL system. Specifically, we design a new Client-Supervised Federated Learning (FedCS) to unravel clients’ bias on instances’ latent representations so that the global model can learn both client-specific and client-agnostic knowledge. Experimental study shows that the FedCS can learn a robust FL global model for the changing data distributions of unseen/test clients. The FedCS’s global model can be directly deployed to the test clients while achieving comparable performance to other personalized FL methods that require model adaptation.

The federated recommendation system is an emerging AI service architecture that provides recommendation services in a privacy-preserving manner. Using user-relation graphs to enhance federated recommendations is a promising topic. However, it is still an open challenge to construct the user-relation graph while preserving data locality-based privacy protection in federated settings. Inspired by a simple motivation, similar users share a similar vision (embeddings) to the same item set, this paper proposes a novel Graph-guided Personalization for Federated Recommendation (GPFedRec). The proposed method constructs a user-relation graph from user-specific personalized item embeddings at the server without accessing the users' interaction records. The personalized item embedding is locally fine-tuned on each device, and then a user-relation graph will be constructed by measuring the similarity among client-specific item embeddings. Without accessing users' historical interactions, we embody the data locality-based privacy protection of vanilla federated learning. Furthermore, a graph-guided aggregation mechanism is designed to leverage the user-relation graph and federated optimization framework simultaneously. Extensive experiments on five benchmark datasets demonstrate GPFedRec's superior performance. The in-depth study validates that GPFedRec can generally improve existing federated recommendation methods as a plugin while keeping user privacy safe. Code is available https://github.com/Zhangcx19/GPFedRec

This paper demonstrates that pre-trained language models (PLMs) are strong foundation models for on-device meteorological variable modeling. We present LM-Weather, a generic approach to taming PLMs, that have learned massive sequential knowledge from the universe of natural language databases, to acquire an immediate capability to obtain highly customized models for heterogeneous meteorological data on devices while keeping high efficiency. Concretely, we introduce a lightweight personalized adapter into PLMs and endows it with weather pattern awareness. During communication between clients and the server, low-rank-based transmission is performed to effectively fuse the global knowledge among devices while maintaining high communication efficiency and ensuring privacy. Experiments on real-wold dataset show that LM-Weather outperforms the state-of-the-art results by a large margin across various tasks (e.g., forecasting and imputation at different scales). We provide extensive and in-depth analyses experiments, which verify that LM-Weather can (1) indeed leverage sequential knowledge from natural language to accurately handle meteorological sequence, (2) allows each devices obtain highly customized models under significant heterogeneity, and (3) generalize under data-limited and out-of-distribution (OOD) scenarios.

Recently, foundation models, particularly large language models (LLMs), have demonstrated an impressive ability to adapt to various tasks by fine-tuning diverse instruction data. Notably, federated foundation models (FedFM) emerge as a privacy preservation method to fine-tune models collaboratively under federated learning (FL) settings by leveraging many distributed datasets with non-IID data. To alleviate communication and computation overhead, parameter-efficient methods are introduced for efficiency, and some research adapted personalization methods to FedFM for better user preferences alignment. However, a critical gap in existing research is the neglect of test-time distribution shifts in real-world applications, and conventional methods for test-time distribution shifts in personalized FL are less effective for FedFM due to their failure to adapt to complex distribution shift scenarios and the requirement to train all parameters. To bridge this gap, we refine the setting in FedFM, termed test-time personalization, which aims to learn personalized federated foundation models on clients while effectively handling test-time distribution shifts simultaneously. To address challenges in this setting, we explore a simple yet effective solution, a Federated Dual-Personalizing Adapter (FedDPA) architecture. By co-working with a foundation model, a global adapter and a local adapter jointly tackle the test-time distribution shifts and client-specific personalization. Additionally, we introduce an instance-wise dynamic weighting mechanism that dynamically integrates the global and local adapters for each test instance during inference, facilitating effective test-time personalization. The effectiveness of the proposed method has been evaluated on benchmark datasets across different NLP tasks.

Federated recommendation system usually trains a global model on the server without direct access to users' private data on their own devices. However, this separation of the recommendation model and users' private data poses a challenge in providing quality service, particularly when it comes to new items, namely cold-start recommendations in federated settings. This paper introduces a novel method called Item-aligned Federated Aggregation (IFedRec) to address this challenge. It is the first research work in federated recommendation to specifically study the cold-start scenario. The proposed method learns two sets of item representations by leveraging item attributes and interaction records simultaneously. Additionally, an item representation alignment mechanism is designed to align two item representations and learn the meta attribute network at the server within a federated learning framework. Experiments on four benchmark datasets demonstrate IFedRec's superior performance for cold-start scenarios. Furthermore, we also verify IFedRec owns good robustness when the system faces limited client participation and noise injection, which brings promising practical application potential in privacy-protection enhanced federated recommendation systems. The implementation code is available

Neighborhood aggregation algorithms, represented as graph convolutional networks, have attained non-negligible success in numerous topological structure-based scenarios with the assumption that the topological structure of the given graph is pre-defined and relatively small. However, a real-world graph generally is a super large graph consisting of many small graphs that are interconnected and overlapping. Which makes graph embedding in real-life industries, by nature, fall into the federated learning scheme. While current graph-based algorithms are only able to capture the individual topology of each natural graph, learning the complete structural information of the merged large graph remains challenging due to the unsustainable computational cost of graph convolutional operations. We propose a tailored federated graph embedding framework to learn the intact structural information of the numerous inherently linked small-scale graphs and the embedding of each node. We leverage graphs with around two and a half million nodes to validate the effectiveness and the correctness of the proposed framework.

This article aims to unify spatial dependency and temporal dependency in a non-Euclidean space while capturing the inner spatial-temporal dependencies for traffic data. For spatial-temporal attribute entities with topological structure, the space-time is consecutive and unified while each node's current status is influenced by its neighbors' past states over variant periods of each neighbor. Most spatial-temporal neural networks for traffic forecasting study spatial dependency and temporal correlation separately in processing, gravely impaired the spatial-temporal integrity, and ignore the fact that the neighbors' temporal dependency period for a node can be delayed and dynamic. To model this actual condition, we propose TraverseNet, a novel spatial-temporal graph neural network, viewing space and time as an inseparable whole, to mine spatial-temporal graphs while exploiting the evolving spatial-temporal dependencies for each node via message traverse mechanisms. Experiments with ablation and parameter studies have validated the effectiveness of the proposed TraverseNet, and the detailed implementation can be found from https://github.com/nnzhan/TraverseNet.

Graph neural networks (GNNs) have shown their superiority in modeling graph data. Owing to the advantages of federated learning, federated graph learning (FGL) enables clients to train strong GNN models in a distributed manner without sharing their private data. A core challenge in federated systems is the non-IID problem, which also widely exists in real-world graph data. For example, local data of clients may come from diverse datasets or even domains, e.g., social networks and molecules, increasing the difficulty for FGL methods to capture commonly shared knowledge and learn a generalized encoder. From real-world graph datasets, we observe that some structural properties are shared by various domains, presenting great potential for sharing structural knowledge in FGL. Inspired by this, we propose FedStar, an FGL framework that extracts and shares the common underlying structure information for inter-graph federated learning tasks. To explicitly extract the structure information rather than encoding them along with the node features, we define structure embeddings and encode them with an independent structure encoder. Then, the structure encoder is shared across clients while the feature-based knowledge is learned in a personalized way, making FedStar capable of capturing more structure-based domain-invariant information and avoiding feature misalignment issues. We perform extensive experiments over both cross-dataset and cross-domain non-IID FGL settings, demonstrating the superiority of FedStar.

Xiuying Chen, Guodong Long, Chongyang Tao, Mingzhe Li, Xin Gao, Chengqi Zhang, Xiangliang Zhang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Image-guided story ending generation (IgSEG) is to generate a story ending based on given story plots and ending image.Existing methods focus on cross-modal feature fusion but overlook reasoning and mining implicit information from story plots and ending image.To tackle this drawback, we propose a multimodal event transformer, an event-based reasoning framework for IgSEG.Specifically, we construct visual and semantic event graphs from story plots and ending image, and leverage event-based reasoning to reason and mine implicit information in a single modality.Next, we connect visual and semantic event graphs and utilize cross-modal fusion to integrate differentmodality features.In addition, we propose a multimodal injector to adaptive pass essential information to decoder.Besides, we present an incoherence detection to enhance the understanding context of a story plot and the robustness of graph modeling for our model.Experimental results show that our method achieves state-of-the-art performance for the image-guided story ending generation.

Text-guided image inpainting (TGII) aims to restore missing regions based on a given text in a damaged image.Existing methods are based on a strong vision encoder and a crossmodal fusion model to integrate cross-modal features.However, these methods allocate most of the computation to visual encoding, while light computation on modeling modality interactions.Moreover, they take cross-modal fusion for depth features, which ignores a finegrained alignment between text and image.Recently, vision-language pre-trained models (VLPM), encapsulating rich cross-modal alignment knowledge, have advanced in most multimodal tasks.In this work, we propose a novel model for TGII by improving cross-modal alignment (CMA).CMA model consists of a VLPM as a vision-language encoder, an image generator and global-local discriminators.To explore cross-modal alignment knowledge for image restoration, we introduce cross-modal alignment distillation and in-sample distribution distillation.In addition, we employ adversarial training to enhance the model to fill the missing region in complicated structures effectively.Experiments are conducted on two popular vision-language datasets.Results show that our model achieves state-of-the-art performance compared with other strong competitors.

Personalized federated learning (PFL) jointly trains a variety of local models through balancing between knowledge sharing across clients and model personalization per client. This paper addresses PFL via explicit disentangling latent representations into two parts to capture the shared knowledge and client-specific personalization, which leads to more reliable and effective PFL. The disentanglement is achieved by a novel Federated Dual Variational Autoencoder (FedDVA), which employs two encoders to infer the two types of representations. FedDVA can produce a better understanding of the trade-off between global knowledge sharing and local personalization in PFL. Moreover, it can be integrated with existing FL methods and turn them into personalized models for heterogeneous downstream tasks. Extensive experiments validate the advantages caused by disentanglement and show that models trained with disentangled representations substantially outperform those vanilla methods.

How to train a generalizable meta-policy by continually learning a sequence of tasks? It is a natural human skill yet challenging to achieve by current reinforcement learning: the agent is expected to quickly adapt to new tasks (plasticity) meanwhile retaining the common knowledge from previous tasks (stability). We address it by "Continual Task Allocation via Sparse Prompting (CoTASP)", which learns over-complete dictionaries to produce sparse masks as prompts extracting a sub-network for each task from a meta-policy network. CoTASP trains a policy for each task by optimizing the prompts and the sub-network weights alternatively. The dictionary is then updated to align the optimized prompts with tasks’ embedding, thereby capturing tasks’ semantic correlations. Hence, relevant tasks share more neurons in the meta-policy network due to similar prompts while cross-task interference causing forgetting is effectively restrained. Given a meta-policy and dictionaries trained on previous tasks, new task adaptation reduces to highly efficient sparse prompting and sub-network finetuning. In experiments, CoTASP achieves a promising plasticity-stability trade-off without storing or replaying any past tasks’ experiences. It outperforms existing continual and multi-task RL methods on all seen tasks, forgetting reduction, and generalization to unseen tasks.

Distribution shift (e.g., task or domain shift) in continual learning (CL) usually results in catastrophic forgetting of previously learned knowledge. Although it can be alleviated by repeatedly replaying buffered data, the every-step replay is time-consuming. In this paper, we study which modules in neural networks are more prone to forgetting by investigating their training dynamics during CL. Our proposed metrics show that only a few modules are more task-specific and sensitive to task change, while others can be shared across tasks as common knowledge. Hence, we attribute forgetting mainly to the former and find that finetuning them only on a small buffer at the end of any CL method can bring non-trivial improvement. Due to the small number of finetuned parameters, such ''Forgetting Prioritized Finetuning (FPF)'' is efficient in computation. We further propose a more efficient and simpler method that entirely removes the every-step replay and replaces them by only $k$-times of FPF periodically triggered during CL. Surprisingly, this ''$k$-FPF'' performs comparably to FPF and outperforms the SOTA CL methods but significantly reduces their computational overhead and cost. In experiments on several benchmarks of class- and domain-incremental CL, FPF consistently improves existing CL methods by a large margin, and $k$-FPF further excels in efficiency without degrading the accuracy. We also empirically studied the impact of buffer size, epochs per task, and finetuning modules on the cost and accuracy of our methods.

To tackle the global climate challenge, it urgently needs to develop a collaborative platform for comprehensive weather forecasting on large-scale meteorological data. Despite urgency, heterogeneous meteorological sensors across countries and regions, inevitably causing multivariate heterogeneity and data exposure, become the main barrier. This paper develops a foundation model across regions capable of understanding complex meteorological data and providing weather forecasting. To relieve the data exposure concern across regions, a novel federated learning approach has been proposed to collaboratively learn a brand-new spatio-temporal Transformer-based foundation model across participants with heterogeneous meteorological data. Moreover, a novel prompt learning mechanism has been adopted to satisfy low-resourced sensors' communication and computational constraints. The effectiveness of the proposed method has been demonstrated on classical weather forecasting tasks using three meteorological datasets with multivariate time series.

Federated recommendation is a new Internet service architecture that aims to provide privacy-preserving recommendation services in federated settings. Existing solutions are used to combine distributed recommendation algorithms and privacy-preserving mechanisms. Thus it inherently takes the form of heavyweight models at the server and hinders the deployment of on-device intelligent models to end-users. This paper proposes a novel Personalized Federated Recommendation (PFedRec) framework to learn many user-specific lightweight models to be deployed on smart devices rather than a heavyweight model on a server. Moreover, we propose a new dual personalization mechanism to effectively learn fine-grained personalization on both users and items. The overall learning process is formulated into a unified federated optimization framework. Specifically, unlike previous methods that share exactly the same item embeddings across users in a federated system, dual personalization allows mild finetuning of item embeddings for each user to generate user-specific views for item representations which can be integrated into existing federated recommendation methods to gain improvements immediately. Experiments on multiple benchmark datasets have demonstrated the effectiveness of PFedRec and the dual personalization mechanism. Moreover, we provide visualizations and in-depth analysis of the personalization techniques in item embedding, which shed novel insights on the design of recommender systems in federated settings. The code is available.

Large-scale retrieval is to recall relevant documents from a huge collection given a query. It relies on representation learning to embed documents and queries into a common semantic encoding space. According to the encoding space, recent retrieval methods based on pre-trained language models (PLM) can be coarsely categorized into either dense-vector or lexicon-based paradigms. These two paradigms unveil the PLMs' representation capability in different granularities, i.e., global sequence-level compression and local word-level contexts, respectively. Inspired by their complementary global-local contextualization and distinct representing views, we propose a new learning framework, Unifier, which unifies dense-vector and lexicon-based retrieval in one model with a dual-representing capability. Experiments on passage retrieval benchmarks verify its effectiveness in both paradigms. A uni-retrieval scheme is further presented with even better retrieval quality. We lastly evaluate the model on BEIR benchmark to verify its transferability.

Heterogeneous federated learning without assuming any structure is challenging due to the conflicts among non-identical data distributions of clients. In practice, clients often comprise near-homogeneous clusters so training a server-side model per cluster mitigates the conflicts. However, FL with client clustering often suffers from “clustering collapse'', i.e., one cluster's model excels on increasing clients, and reduces to single-model FL. Moreover, cluster-wise models hinder knowledge sharing between clusters and each model depends on fewer clients. Furthermore, the static clustering assumption on data may not hold for dynamically changing models, which are sensitive to cluster imbalance/initialization or outliers. To address these challenges, we propose ''Clustered Additive Modeling (CAM)'', which applies a globally shared model $\Theta_g$ on top of the cluster-wise models $\Theta_{1:K}$, i.e., $y=h(x;\Theta_g)+f(x;\Theta_k)$ for clients of cluster-$k$. The global model captures the features shared by all clusters so $\Theta_{1:K}$ are enforced to focus on the difference among clusters. To train CAM, we develop a novel Fed-CAM algorithm that alternates between client clustering and training global/cluster models to predict the residual of each other. We can easily modify any existing clustered FL methods by CAM and significantly improve their performance without ‘’clustering collapse'' in different non-IID settings. We also provide a convergence analysis of Fed-CAM algorithm.

Federated learning (FL) is an effective machine learning paradigm where multiple clients can train models based on heterogeneous data in a decentralized manner without accessing their private data. However, existing FL systems undergo performance deterioration due to feature-level test-time shifts, which are well investigated in centralized settings but rarely studied in FL. The common non-IID issue in FL usually refers to inter-client heterogeneity during training phase, while the test-time shift refers to the intra-client heterogeneity during test phase. Although the former is always deemed to be notorious for FL, there is still a wealth of useful information delivered by heterogeneous data sources, which may potentially help alleviate the latter issue. To explore the possibility of using inter-client heterogeneity in handling intra-client heterogeneity, we firstly propose a contrastive learning-based FL framework, namely FedICON, to capture invariant knowledge among heterogeneous clients and consistently tune the model to adapt to test data. In FedICON, each client performs sample-wise supervised contrastive learning during the local training phase, which enhances sample-wise invariance encoding ability. Through global aggregation, the invariance extraction ability can be mutually boosted among inter-client heterogeneity. During the test phase, our test-time adaptation procedure leverages unsupervised contrastive learning to guide the model to smoothly generalize to test data under intra-client heterogeneity. Extensive experiments validate the effectiveness of the proposed FedICON in taming heterogeneity to handle test-time shift problems.

Abstract Multivariate time series classification is a critical problem in data mining with broad applications. It requires harnessing the inter-relationship of multiple variables and various ranges of temporal dependencies to assign the correct classification label of the time series. Multivariate time series may come from a wide range of sources and be used in various scenarios, bringing the classifier challenge of temporal representation learning. We propose a novel convolutional neural network architecture called Attentional Gated Res2Net for multivariate time series classification. Our model uses hierarchical residual-like connections to achieve multi-scale receptive fields and capture multi-granular temporal information. The gating mechanism enables the model to consider the relations between the feature maps extracted by receptive fields of multiple sizes for information fusion. Further, we propose two types of attention modules, channel-wise attention and block-wise attention, to better leverage the multi-granular temporal patterns. Our experimental results on 14 benchmark multivariate time-series datasets show that our model outperforms several baselines and state-of-the-art methods by a large margin. Our model outperforms the SOTA by a large margin, the classification accuracy of our model is 10.16% better than the SOTA model. Besides, we demonstrate that our model improves the performance of existing models when used as a plugin. Further, based on our experiments and analysis, we provide practical advice on applying our model to a new problem.

Graph convolutional networks are becoming indispensable for deep learning from graph-structured data. Most of the existing graph convolutional networks share two big shortcomings. First, they are essentially low-pass filters, thus the potentially useful middle and high frequency band of graph signals are ignored. Second, the bandwidth of existing graph convolutional filters is fixed. Parameters of a graph convolutional filter only transform the graph inputs without changing the curvature of a graph convolutional filter function. In reality, we are uncertain about whether we should retain or cut off the frequency at a certain point unless we have expert domain knowledge. In this paper, we propose Automatic Graph Convolutional Networks (AutoGCN) to capture the full spectrum of graph signals and automatically update the bandwidth of graph convolutional filters. While it is based on graph spectral theory, our AutoGCN is also localized in space and has a spatial form. Experimental results show that AutoGCN achieves significant improvement over baseline methods which only work as low-pass filters.

Abstract Personalized decision-making can be implemented in a Federated learning (FL) framework that can collaboratively train a decision model by extracting knowledge across intelligent clients, e.g. smartphones or enterprises. FL can mitigate the data privacy risk of collaborative training since it merely collects local gradients from users without access to their data. However, FL is fragile in the presence of statistical heterogeneity that is commonly encountered in personalized decision making, e.g., non-IID data over different clients. Existing FL approaches usually update a single global model to capture the shared knowledge of all users by aggregating their gradients, regardless of the discrepancy between their data distributions. By comparison, a mixture of multiple global models could capture the heterogeneity across various clients if assigning the client to different global models (i.e., centers) in FL. To this end, we propose a novel multi-center aggregation mechanism to cluster clients using their models’ parameters. It learns multiple global models from data as the cluster centers, and simultaneously derives the optimal matching between users and centers. We then formulate it as an optimization problem that can be efficiently solved by a stochastic expectation maximization (EM) algorithm. Experiments on multiple benchmark datasets of FL show that our method outperforms several popular baseline methods. The experimental source codes are publicly available on the Github repository (GitHub repository: https://github.com/mingxuts/multi-center-fed-learning ).

Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients' knowledge occurs in the gradient space. For example, clients may differ in terms of data distribution, network latency, input/output space, and/or model architecture, which can easily lead to the misalignment of their local gradients. To improve the tolerance to heterogeneity, we propose a novel federated prototype learning (FedProto) framework in which the clients and server communicate the abstract class prototypes instead of the gradients. FedProto aggregates the local prototypes collected from different clients, and then sends the global prototypes back to all clients to regularize the training of local models. The training on each client aims to minimize the classification error on the local data while keeping the resulting local prototypes sufficiently close to the corresponding global ones. Moreover, we provide a theoretical analysis to the convergence rate of FedProto under non-convex objectives. In experiments, we propose a benchmark setting tailored for heterogeneous FL, with FedProto outperforming several recent FL approaches on multiple datasets.

Generating new events given context with correlated ones plays a crucial role in many eventcentric reasoning tasks.Existing works either limit their scope to specific scenarios or overlook event-level correlations.In this paper, we propose to pre-train a general Correlationaware context-to-Event Transformer (ClarET) for event-centric reasoning.To achieve this, we propose three novel event-centric objectives, i.e., whole event recovering, contrastive eventcorrelation encoding and prompt-based event locating, which highlight event-level correlations with effective training.The proposed ClarET is applicable to a wide range of eventcentric reasoning scenarios, considering its versatility of (i) event-correlation types (e.g., causal, temporal, contrast), (ii) application formulations (i.e., generation and classification), and (iii) reasoning types (e.g., abductive, counterfactual and ending reasoning).Empirical fine-tuning results, as well as zero-and fewshot learning, on 9 benchmarks (5 generation and 4 classification tasks covering 4 reasoning types with diverse event correlations), verify its effectiveness and generalization ability.

Multivariate time series classification is a critical problem in data mining with broad applications. We design a novel convolutional neural network architecture, Attentional Gated Res2Net, for robust multivariate time series classification. AGRes2Net uses hierarchical residual-like connections to achieve multi-scale receptive fields and to capture multi- granular temporal patterns. It further employs the gated mechanism to harness inter-relationship between feature maps. We propose two types of attention modules, namely channel-wise attention and block-wise attention, to leverage the multi-granular temporal patterns. Our experiments on six benchmark datasets demonstrate that AGRes2Net not only outperforms several baselines and state-of-the-art methods but also improves the classification accuracy of existing models when used as a plug-in.

Positive and Unlabeled learning (PU learning) trains a binary classifier based on only positive (P) and unlabeled (U) data, where the unlabeled data contains positive or negative samples. Previous importance reweighting approaches treat all unlabeled samples as weighted negative samples, achieving state-of-the-art performance. However, in this paper, we surprisingly find that the classifier could misclassify negative samples in U data as positive ones at the late training stage by weight adjustment. Motivated by this discovery, we leverage Semi-Supervised Learning (SSL) to address this performance degradation problem. To this end, we propose a novel SSL-based framework to tackle PU learning. Firstly, we introduce the dynamic increasing sampling strategy to progressively select both negative and positive samples from U data. Secondly, we adopt MixMatch to take full advantage of the unchosen samples in U data. Finally, we propose the Co-learning strategy that iteratively trains two independent networks with the selected samples to avoid the confirmation bias. Experimental results on four benchmark datasets demonstrate the effectiveness and superiority of our approach when compared with other state-of-the-art methods.

Reinforcement learning (RL) is inefficient on long-horizon tasks due to sparse rewards and its policy can be fragile to slightly perturbed environments. We address these challenges via a curriculum of tasks with coupled environments, generated by two policies trained jointly with RL: (1) a co-operative planning policy recursively decomposing a hard task into a coarse-to-fine sub-task tree; and (2) an adversarial policy modifying the environment in each sub-task. They are complementary to acquire more informative feedback for RL: (1) provides dense reward of easier sub-tasks while (2) modifies sub-tasks’ environments to be more challenging and diverse. Conversely, they are trained by RL’s dense feedback on sub-tasks so their generated curriculum keeps adaptive to RL’s progress. The sub-task tree enables an easy-to-hard curriculum for every policy: its top-down construction gradually increases sub-tasks the planner needs to generate, while the adversarial training between the environment and RL follows a bottom-up traversal that starts from a dense sequence of easier sub-tasks allowing more frequent environment changes. We compare EAT-C with RL/planning targeting similar problems and methods with environment generators or adversarial agents. Extensive experiments on diverse tasks demonstrate the advantages of our method on improving RL’s efficiency and generalization.

Knowledge sharing and model personalization are two key components in the conceptual framework of personalized federated learning (PFL). Existing PFL methods focus on proposing new model personalization mechanisms while simply implementing knowledge sharing by aggregating models from all clients, regardless of their relation graph. This paper aims to enhance the knowledge-sharing process in PFL by leveraging the graph-based structural information among clients. We propose a novel structured federated learning (SFL) framework to learn both the global and personalized models simultaneously using client-wise relation graphs and clients' private data. We cast SFL with graph into a novel optimization problem that can model the client-wise complex relations and graph-based structural topology by a unified framework. Moreover, in addition to using an existing relation graph, SFL could be expanded to learn the hidden relations among clients. Experiments on traffic and image benchmark datasets can demonstrate the effectiveness of the proposed method.

This work studies temporal reading comprehension (TRC), which reads a free-text passage and answers temporal ordering questions.Precise question understanding is critical for temporal reading comprehension.For example, the question "What happened before the victory" and "What happened after the victory" share almost all words except one, while their answers are totally different.Moreover, even if two questions query about similar temporal relations, different varieties might also lead to various answers.For example, although both the question "What usually happened during the press release?" and "What might happen during the press release" query events which happen after the press release, they convey divergent semantics.To this end, we propose a novel reading comprehension approach with precise question understanding.Specifically, a temporal ordering question is embedded into two vectors to capture the referred event and the temporal relation.Then we evaluate the temporal relation between candidate events and the referred event based on that.Such fine-grained representations offer two benefits.First, it enables a better understanding of the question by focusing on different elements of a question.Second, it provides good interpretability when evaluating temporal relations.Furthermore, we also harness an auxiliary contrastive loss for representation learning of temporal relations, which aims to distinguish relations with subtle but critical changes.The proposed approach outperforms strong baselines and achieves state-of-the-art performance on the TORQUE dataset.It also increases the accuracy of four pre-trained language models (BERT base, BERT large, RoBERTa base, and RoBETRa large), demonstrating its generic effectiveness on divergent models.

Federated Learning (FL) is a machine learning paradigm that allows decentralized clients to learn collaboratively without sharing their private data. However, excessive computation and communication demands pose challenges to current FL frameworks, especially when training large-scale models. To prevent these issues from hindering the deployment of FL systems, we propose a lightweight framework where clients jointly learn to fuse the representations generated by multiple fixed pre-trained models rather than training a large-scale model from scratch. This leads us to a more practical FL problem by considering how to capture more client-specific and class-relevant information from the pre-trained models and jointly improve each client's ability to exploit those off-the-shelf models. Here, we design a Federated Prototype-wise Contrastive Learning (FedPCL) approach which shares knowledge across clients through their class prototypes and builds client-specific representations in a prototype-wise contrastive manner. Sharing prototypes rather than learnable model parameters allows each client to fuse the representations in a personalized way while keeping the shared knowledge in a compact form for efficient communication. We perform a thorough evaluation of the proposed FedPCL in the lightweight framework, measuring and visualizing its ability to fuse various pre-trained models on popular FL datasets.

Event correlation reasoning infers whether a natural language paragraph containing multiple events conforms to human common sense. For example, “Andrew was very drowsy, so he took a long nap, and now he is very alert” is sound and reasonable. In contrast, “Andrew was very drowsy, so he stayed up a long time, now he is very alert” does not comply with human common sense. Such reasoning capability is essential for many downstream tasks, such as script reasoning, abductive reasoning, narrative incoherence, story cloze test, etc. However, conducting event correlation reasoning is challenging due to a lack of large amounts of diverse event-based knowledge and difficulty in capturing correlation among multiple events. In this paper, we propose EventBERT, a pre-trained model to encapsulate eventuality knowledge from unlabeled text. Specifically, we collect a large volume of training examples by identifying natural language paragraphs that describe multiple correlated events and further extracting event spans in an unsupervised manner. We then propose three novel event- and correlation-based learning objectives to pre-train an event correlation model on our created training corpus. Experimental results show EventBERT outperforms strong baselines on four downstream tasks, and achieves state-of-the-art results on most of them. Moreover, it outperforms existing pre-trained models by a large margin, e.g., 6.5 ∼ 23%, in zero-shot learning of these tasks.

We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings. Compared to the well-studied many-class many-shot and few-class few-shot problems, the MCFS problem commonly occurs in practical applications but has been rarely studied in previous literature. It brings new challenges of distinguishing between many classes given only a few training samples per class. In this article, we leverage the class hierarchy as a prior knowledge to train a coarse-to-fine classifier that can produce accurate predictions for MCFS problem in both settings. The propose model, “memory-augmented hierarchical-classification network (MahiNet)”, performs coarse-to-fine classification where each coarse class can cover multiple fine classes. Since it is challenging to directly distinguish a variety of fine classes given few-shot data per class, MahiNet starts from learning a classifier over coarse-classes with more training data whose labels are much cheaper to obtain. The coarse classifier reduces the searching range over the fine classes and thus alleviates the challenges from “many classes”. On architecture, MahiNet first deploys a convolutional neural network (CNN) to extract features. It then integrates a memory-augmented attention module and a multi-layer perceptron (MLP) together to produce the probabilities over coarse and fine classes. While the MLP extends the linear classifier, the attention module extends the KNN classifier, both together targeting the “few-shot” problem. We design several training strategies of MahiNet for supervised learning and meta-learning. In addition, we propose two novel benchmark datasets “mcfsImageNet” (as a subset of ImageNet) and “mcfsOmniglot” (re-splitted Omniglot) specially designed for MCFS problem. In experiments, we show that MahiNet outperforms several state-of-the-art models (e.g., prototypical networks and relation networks) on MCFS problems in both supervised learning and meta-learning.

Zero-shot learning (ZSL) refers to the problem of learning to classify instances from novel classes (unseen) that are absent in the training set (seen). Most ZSL methods infer the correlation between visual features and attributes to train the classifier for unseen classes. They may have a strong bias towards seen classes during training. Meta-learning has been introduced to mitigate the basis, but meta-ZSL methods are inapplicable when tasks used for training are sampled from diverse distributions. In this regard, we propose a novel Task-aligned Generative Meta-learning model for Zero-shot learning (TGMZ), aiming to mitigate the potentially biased training and to enable meta-ZSL to accommodate real-world datasets that contain diverse distributions. Specifically, TGMZ incorporates an attribute-conditioned task-wise distribution alignment network that projects tasks into a unified distribution to deliver an unbiased model. Our experiments show TGMZ achieves a relative improvement of 2.1%, 3.0%, 2.5%, and 7.6% over state-of-the-art algorithms on AWA1, AWA2, CUB, and aPY datasets, respectively. Overall, TGMZ outperforms competitors by 3.6% in the generalized zero-shot learning (GZSL) setting and 7.9% in our proposed fusion-ZSL setting.

Hao Huang, Xiubo Geng, Jian Pei, Guodong Long, Daxin Jiang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Sequential diagnosis prediction on the Electronic Health Record (EHR) has been proven crucial for predictive analytics in the medical domain. EHR data, sequential records of a patient’s interactions with healthcare systems, has numerous inherent characteristics of temporality, irregularity and data insufficiency. Some recent works train healthcare predictive models by making use of sequential information in EHR data, but they are vulnerable to irregular, temporal EHR data with the states of admission/discharge from hospital, and insufficient data. To mitigate this, we propose an end-to-end robust transformer-based model called SETOR, which exploits neural ordinary differential equation to handle both irregular intervals between a patient’s visits with admitted timestamps and length of stay in each visit, to alleviate the limitation of insufficient data by integrating medical ontology, and to capture the dependencies between the patient’s visits by employing multi-layer transformer blocks. Experiments conducted on two real-world healthcare datasets show that, our sequential diagnoses prediction model SETOR not only achieves better predictive results than previous state-of-the-art approaches, irrespective of sufficient or insufficient training data, but also derives more interpretable embeddings of medical codes. The experimental codes are available at the GitHub repository1.1Github repository: https://github.com/Xueping/SETOR

Goal-conditioned reinforcement learning (RL) usually suffers from sparse reward and inefficient exploration in long-horizon tasks. Planning can find the shortest path to a distant goal that provides dense reward/guidance but is inaccurate without a precise environment model. We show that RL and planning can collaboratively learn from each other to overcome their own drawbacks. In ''CO-PILOT'', a learnable path-planner and an RL agent produce dense feedback to train each other on a curriculum of tree-structured sub-tasks. Firstly, the planner recursively decomposes a long-horizon task to a tree of sub-tasks in a top-down manner, whose layers construct coarse-to-fine sub-task sequences as plans to complete the original task. The planning policy is trained to minimize the RL agent's cost of completing the sequence in each layer from top to bottom layers, which gradually increases the sub-tasks and thus forms an easy-to-hard curriculum for the planner. Next, a bottom-up traversal of the tree trains the RL agent from easier sub-tasks with denser rewards on bottom layers to harder ones on top layers and collects its cost on each sub-task train the planner in the next episode. CO-PILOT repeats this mutual training for multiple episodes before switching to a new task, so the RL agent and planner are fully optimized to facilitate each other's training. We compare CO-PILOT with RL (SAC, HER, PPO), planning (RRT*, NEXT, SGT), and their combination (SoRB) on navigation and continuous control tasks. CO-PILOT significantly improves the success rate and sample efficiency.

Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks, but these graphs are usually incomplete, urging auto-completion of them (a.k.a. knowledge graph completion). Prevalent graph embedding approaches, e.g., TransE, learn structured knowledge via representing graph elements (i.e., entities/relations) into dense embeddings and capturing their triple-level relationship with spatial distance. However, they are hardly generalizable to the elements never visited in training and are intrinsically vulnerable to graph incompleteness. In contrast, textual encoding approaches, e.g., KG-BERT, resort to graph triple’s text and triple-level contextualized representations. They are generalizable enough and robust to the incompleteness, especially when coupled with pre-trained encoders. But two major drawbacks limit the performance: (1) high overheads due to the costly scoring of all possible triples in inference, and (2) a lack of structured knowledge in the textual encoder. In this paper, we follow the textual encoding paradigm and aim to alleviate its drawbacks by augmenting it with graph embedding techniques – a complementary hybrid of both paradigms. Specifically, we partition each triple into two asymmetric parts as in translation-based graph embedding approach, and encode both parts into contextualized representations by a Siamese-style textual encoder. Built upon the representations, our model employs both deterministic classifier and spatial measurement for representation and structure learning respectively. It thus reduces the overheads by reusing graph elements’ embeddings to avoid combinatorial explosion, and enhances structured knowledge by exploring the spatial characteristics. Moreover, we develop a self-adaptive ensemble scheme to further improve the performance by incorporating triple scores from an existing graph embedding model. In experiments, we achieve state-of-the-art performance on three benchmarks and a zero-shot dataset for link prediction, with highlights of inference costs reduced by 1-2 orders of magnitude compared to a sophisticated textual encoding method.

Suicide is a critical issue in modern society. Early detection and prevention of suicide attempts should be addressed to save people's life. Current suicidal ideation detection (SID) methods include clinical methods based on the interaction between social workers or experts and the targeted individuals and machine learning techniques with feature engineering or deep learning for automatic detection based on online social contents. This article is the first survey that comprehensively introduces and discusses the methods from these categories. Domain-specific applications of SID are reviewed according to their data sources, i.e., questionnaires, electronic health records, suicide notes, and online user content. Several specific tasks and data sets are introduced and summarized to facilitate further research. Finally, we summarize the limitations of current work and provide an outlook of further research directions.

The brain–computer interface (BCI) control technology that utilizes motor imagery to perform the desired action instead of manual operation will be widely used in smart environments. However, most of the research lacks robust feature representation of multi-channel EEG series, resulting in low intention recognition accuracy. This article proposes an EEG2Image based Denoised-ConvNets (called EID) to enhance feature representation of the intention recognition task. Specifically, we perform signal decomposition, slicing, and image mapping to decrease the noise from the irrelevant frequency bands. After that, we construct the Denoised-ConvNets structure to learn the colorspace and spatial variations of image objects without cropping new training images precisely. Toward further utilizing the color and spatial transformation layers, the colorspace and colored area of image objects have been enhanced and enlarged, respectively. In the multi-classification scenario, extensive experiments on publicly available EEG datasets confirm that the proposed method has better performance than state-of-the-art methods.

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.

Neighborhood aggregation algorithms like spectral graph convolutional networks (GCNs) formulate graph convolutions as a symmetric Laplacian smoothing operation to aggregate the feature information of one node with that of its neighbors. While they have achieved great success in semi-supervised node classification on graphs, current approaches suffer from the over-smoothing problem when the depth of the neural networks increases, which always leads to a noticeable degradation of performance. To solve this problem, we present graph convolutional ladder-shape networks (GCLN), a novel graph neural network architecture that transmits messages from shallow layers to deeper layers to overcome the over-smoothing problem and dramatically extend the scale of the neural networks with improved performance. We have validated the effectiveness of proposed GCLN at a node-wise level with a semi-supervised task (node classification) and an unsupervised task (node clustering), and at a graph-wise level with graph classification by applying a differentiable pooling operation. The proposed GCLN outperforms original GCNs, deep GCNs and other state-of-the-art GCN-based models for all three tasks, which were designed from various perspectives on six real-world benchmark data sets.

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly labeled data, which however could be incompetent when there is only one sentence in a bag. In this paper, we propose a brand-new light-weight neural framework to address the distantly supervised relation extraction problem and alleviate the defects in previous selective attention framework. Specifically, in the proposed framework, 1) we use an entity-aware word embedding method to integrate both relative position information and head/tail entity embeddings, aiming to highlight the essence of entities for this task; 2) we develop a self-attention mechanism to capture the rich contextual dependencies as a complement for local dependencies captured by piecewise CNN; and 3) instead of using selective attention, we design a pooling-equipped gate, which is based on rich contextual representations, as an aggregator to generate bag-level representation for final relation classification. Compared to selective attention, one major advantage of the proposed gating mechanism is that, it performs stably and promisingly even if only one sentence appears in a bag and thus keeps the consistency across all training examples. The experiments on NYT dataset demonstrate that our approach achieves a new state-of-the-art performance in terms of both AUC and top-n precision metrics.

The goal of zero-shot learning (ZSL) is to train a model to classify samples of classes that were not seen during training. To address this challenging task, most ZSL methods relate unseen test classes to seen(training) classes via a pre-defined set of attributes that can describe all classes in the same semantic space, so the knowledge learned on the training classes can be adapted to unseen classes. In this paper, we aim to optimize the attribute space for ZSL by training a propagation mechanism to refine the semantic attributes of each class based on its neighbors and related classes on a graph of classes. We show that the propagated attributes can produce classifiers for zero-shot classes with significantly improved performance in different ZSL settings. The graph of classes is usually free or very cheap to acquire such as WordNet or ImageNet classes. When the graph is not provided, given pre-defined semantic embeddings of the classes, we can learn a mechanism to generate the graph in an end-to-end manner along with the propagation mechanism. However, this graph-aided technique has not been well-explored in the literature. In this paper, we introduce the “attribute propagation network (APNet)”, which is composed of 1) a graph propagation model generating attribute vector for each class and 2) a parameterized nearest neighbor (NN) classifier categorizing an image to the class with the nearest attribute vector to the image's embedding. For better generalization over unseen classes, different from previous methods, we adopt a meta-learning strategy to train the propagation mechanism and the similarity metric for the NN classifier on multiple sub-graphs, each associated with a classification task over a subset of training classes. In experiments with two zero-shot learning settings and five benchmark datasets, APNet achieves either compelling performance or new state-of-the-art results.

The aim of visual relation detection is to provide a comprehensive understanding of an image by describing all the objects within the scene, and how they relate to each other, in < object-predicate-object > form; for example, < person-lean on-wall > . This ability is vital for image captioning, visual question answering, and many other applications. However, visual relationships have long-tailed distributions and, thus, the limited availability of training samples is hampering the practicability of conventional detection approaches. With this in mind, we designed a novel model for visual relation detection that works in one-shot settings. The embeddings of objects and predicates are extracted through a network that includes a feature-level attention mechanism. Attention alleviates some of the problems with feature sparsity, and the resulting representations capture more discriminative latent features. The core of our model is a dual graph neural network that passes and aggregates the context information of predicates and objects in an episodic training scheme to improve recognition of the one-shot predicates and then generate the triplets. To the best of our knowledge, we are the first to center on the viability of one-shot learning for visual relation detection. Extensive experiments on two newly-constructed datasets show that our model significantly improved the performance of two tasks PredCls and SGCls from 2.8% to 12.2% compared with state-of-the-art baselines.

Many graph embedding approaches have been proposed for knowledge graph completion via link prediction.Among those, translating embedding approaches enjoy the advantages of lightweight structure, high efficiency and great interpretability.Especially when extended to complex vector space, they show the capability in handling various relation patterns including symmetry, antisymmetry, inversion and composition.However, previous translating embedding approaches defined in complex vector space suffer from two main issues: 1) representing and modeling capacities of the model are limited by the translation function with rigorous multiplication of two complex numbers; and 2) embedding ambiguity caused by one-to-many relations is not explicitly alleviated.In this paper, we propose a relation-adaptive translation function built upon a novel weighted product in complex space, where the weights are learnable, relation-specific and independent to embedding size.The translation function only requires eight more scalar parameters each relation, but improves expressive power and alleviates embedding ambiguity problem.Based on the function, we then present our Relation-adaptive translating Embedding (RatE) approach to score each graph triple.Moreover, a novel negative sampling method is proposed to utilize both prior knowledge and self-adversarial learning for effective optimization.Experiments verify RatE achieves state-of-the-art performance on four link prediction benchmarks.

Wrong labeling problem and long-tail relations are two main challenges caused by distant supervision in relation extraction.Recent works alleviate the wrong labeling by selective attention via multi-instance learning, but cannot well handle long-tail relations even if hierarchies of the relations are introduced to share knowledge.In this work, we propose a novel neural network, Collaborating Relation-augmented Attention (CoRA), to handle both the wrong labeling and long-tail relations.Particularly, we first propose relation-augmented attention network as base model.It operates on sentence bag with a sentence-to-relation attention to minimize the effect of wrong labeling.Then, facilitated by the proposed base model, we introduce collaborating relation features shared among relations in the hierarchies to promote the relation-augmenting process and balance the training data for long-tail relations.Besides the main training objective to predict the relation of a sentence bag, an auxiliary objective is utilized to guide the relationaugmenting process for a more accurate bag-level representation.In the experiments on the popular benchmark dataset NYT, the proposed CoRA improves the prior state-of-the-art performance by a large margin in terms of Precision@N, AUC and [email protected] analyses verify its superior capability in handling long-tail relations in contrast to the competitors.

In this work, we aim at equipping pre-trained language models with structured knowledge.We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs.Building upon entity-level masked language models, our first contribution is an entity masking scheme that exploits relational knowledge underlying the text.This is fulfilled by using a linked knowledge graph to select informative entities and then masking their mentions.In addition, we use knowledge graphs to obtain distractors for the masked entities, and propose a novel distractor-suppressed ranking objective that is optimized jointly with masked language model.In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training, to inject language models with structured knowledge via learning from raw text.It is more efficient than retrieval-based methods that perform entity linking and integration during finetuning and inference, and generalizes more effectively than the methods that directly learn from concatenated graph triples.Experiments show that our proposed model achieves improved performance on five benchmarks, including question answering and knowledge base completion.

Electronic health records (EHRs) are longitudinal records of a patient's interactions with healthcare systems. A patient's EHR data is organized as a three-level hierarchy from top to bottom: patient journey - all the experiences of diagnoses and treatments over a period of time; individual visit - a set of medical codes in a particular visit; and medical code - a specific record in the form of medical codes. As EHRs begin to amass in millions, the potential benefits, which these data might hold for medical research and medical outcome prediction, are staggering - including, for example, predicting future admissions to hospitals, diagnosing illnesses or determining the efficacy of medical treatments. Each of these analytics tasks requires a domain knowledge extraction method to transform the hierarchical patient journey into a vector representation for further prediction procedure. The representations should embed a sequence of visits and a set of medical codes with a specific timestamp, which are crucial to any downstream prediction tasks. Hence, expressively powerful representations are appealing to boost learning performance. To this end, we propose a novel self-attention mechanism that captures the contextual dependency and temporal relationships within a patient's healthcare journey. An end-to-end bidirectional temporal encoder network (BiteNet) then learns representations of the patient's journeys, based solely on the proposed attention mechanism. We have evaluated the effectiveness of our methods on two supervised prediction and two unsupervised clustering tasks with a real-world EHR dataset. The empirical results demonstrate the proposed BiteNet model produces higher-quality representations than state-of-the-art baseline methods.

Graph embedding has shown its effectiveness to represent graph information and capture deep relationships in graph data. Most recent graph embedding methods focus on attributed graphs, since they preserve both structure and content information in the network. However, corruption can exist in the graph structure as well as the node content of the graph, and both can lead to inferior embedding results. Unfortunately, few existing graph embedding algorithms have considered the corruption problem, and to the best of our knowledge, none has studied structural corruption in attributed graphs, including missing and redundant edges. This field is difficult for previous methods, mainly due to two challenges: (1) the existence of various corruption causes has made it difficult to recognize corruptions in graphs, and (2) the complexity of graph-structured data has increased the difficulty of handling corruption therein for graph embedding methods. These facts lead us here to propose a novel autoencoder-based graph embedding approach, which is robust against structural corruption. Our idea comes from the recent discovery of memorization effects in deep learning. Namely, deep neural networks prefer to fit clean data first, before they over-fit corrupted data. Specifically, we train two autoencoders simultaneously and let them learn the reliability of the edges in the graph from each other. The two autoencoders would evaluate the edges according to their reconstructed structure and manipulate this by devaluing those distrusted edges to update the structure information. The updated structure would be used further in the next iteration as the ground-truth of its peer-network. Experiments on different versions of real-world graphs show state-of-the-art results and demonstrate the robustness of our model against structural corruption.

Many algorithms for Knowledge-Based Question Answering (KBQA) depend on semantic parsing, which translates a question to its logical form. When only weak supervision is provided, it is usually necessary to search valid logical forms for model training. However, a complex question typically involves a huge search space, which creates two main problems: 1) the solutions limited by computation time and memory usually reduce the success rate of the search, and 2) spurious logical forms in the search results degrade the quality of training data. These two problems lead to a poorly-trained semantic parsing model. In this work, we propose an effective search method for weakly supervised KBQA based on operator prediction for questions. With search space constrained by predicted operators, sufficient search paths can be explored, more valid logical forms can be derived, and operators possibly causing spurious logical forms can be avoided. As a result, a larger proportion of questions in a weakly supervised training set are equipped with logical forms, and fewer spurious logical forms are generated. Such high-quality training data directly contributes to a better semantic parsing model. Experimental results on one of the largest KBQA datasets (i.e., CSQA) verify the effectiveness of our approach and deliver a new state-of-the-art performance.

Recent few-shot learning works focus on training a model with prior meta-knowledge to fast adapt to new tasks with unseen classes and samples. However, conventional time-series classification algorithms fail to tackle the few-shot scenario. Existing few-shot learning methods are proposed to tackle image or text data, and most of them are neural-based models that lack interpretability. This paper proposes an interpretable neural-based framework, namely Dual Prototypical Shapelet Networks (DPSN) for few-shot time-series classification, which not only trains a neural network-based model but also interprets the model from dual granularity: 1) global overview using representative time series samples, and 2) local highlights using discriminative shapelets. In particular, the generated dual prototypical shapelets consist of representative samples that can mostly demonstrate the overall shapes of all samples in the class and discriminative partial-length shapelets that can be used to distinguish different classes. We have derived 18 few-shot TSC datasets from public benchmark datasets and evaluated the proposed method by comparing with baselines. The DPSN framework outperforms state-of-the-art time-series classification methods, especially when training with limited amounts of data. Several case studies have been given to demonstrate the interpret ability of our model.

Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time series forecasting is that its variables depend on one another but, upon looking closely, it is fair to say that existing methods fail to fully exploit latent spatial dependencies between pairs of variables. In recent years, meanwhile, graph neural networks (GNNs) have shown high capability in handling relational dependencies. GNNs require well-defined graph structures for information propagation which means they cannot be applied directly for multivariate time series where the dependencies are not known in advance. In this paper, we propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module, into which external knowledge like variable attributes can be easily integrated. A novel mix-hop propagation layer and a dilated inception layer are further proposed to capture the spatial and temporal dependencies within the time series. The graph learning, graph convolution, and temporal convolution modules are jointly learned in an end-to-end framework. Experimental results show that our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information.

Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep Reinforcement Learning (CHDRL) framework that can learn a policy by integrating the advantages of heterogeneous agents. Specifically, we propose a cooperative learning framework that classifies heterogeneous agents into two classes: global agents and local agents. Global agents are off-policy agents that can utilize experiences from the other agents. Local agents are either on-policy agents or population-based evolutionary algorithms (EAs) agents that can explore the local area effectively. We employ global agents, which are sample-efficient, to guide the learning of local agents so that local agents can benefit from the sample-efficient agents and simultaneously maintain their advantages, e.g., stability. Global agents also benefit from effective local searches. Experimental studies on a range of continuous control tasks from the Mujoco benchmark show that CHDRL achieves better performance compared with state-of-the-art baselines.

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph-analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes, which unfortunately may lead to inferior representation in many cases. In this article, we present a novel adversarially regularized framework for graph embedding. By employing the graph convolutional network as an encoder, our framework embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph. The adversarial training principle is applied to enforce our latent codes to match a prior Gaussian or uniform distribution. Based on this framework, we derive two variants of the adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, and adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively. We also exploit other potential variations of ARGA and ARVGA to get a deeper understanding of our designs. Experimental results that compared 12 algorithms for link prediction and 20 algorithms for graph clustering validate our solutions.

Semi-supervised learning is crucial for alleviating labelling burdens in people-centric sensing. However, humangenerated data inherently suffer from distribution shift in semi-supervised learning due to the diverse biological conditions and behavior patterns of humans. To address this problem, we propose a generic distributionally robust model for semi-supervised learning on distributionally shifted data. Considering both the discrepancy and the consistency between the labeled data and the unlabeled data, we learn the latent features that reduce person-specific discrepancy and preserve task-specific consistency. We evaluate our model in a variety of people-centric recognition tasks on real-world datasets, including intention recognition, activity recognition, muscular movement recognition and gesture recognition. The experiment results demonstrate that the proposed model outperforms the state-of-the-art methods.

Tao Shen, Xiubo Geng, Tao Qin, Daya Guo, Duyu Tang, Nan Duan, Guodong Long, Daxin Jiang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

In longitudinal electronic health records (EHRs), the event records of a patient are distributed over a long period of time and the temporal relations between the events reflect sufficient domain knowledge to benefit prediction tasks such as the rate of inpatient mortality. Medical concept embedding as a feature extraction method that transforms a set of medical concepts with a specific time stamp into a vector, which will be fed into a supervised learning algorithm. The quality of the embedding significantly determines the learning performance over the medical data. In this paper, we propose a medical concept embedding method based on applying a self-attention mechanism to represent each medical concept. We propose a novel attention mechanism which captures the contextual information and temporal relationships between medical concepts. A light-weight neural net, "Temporal Self-Attention Network (TeSAN)", is then proposed to learn medical concept embedding based solely on the proposed attention mechanism. To test the effectiveness of our proposed methods, we have conducted clustering and prediction tasks on two public EHRs datasets comparing TeSAN against five state-of-the-art embedding methods. The experimental results demonstrate that the proposed TeSAN model is superior to all the compared methods. To the best of our knowledge, this work is the first to exploit temporal self-attentive relations between medical events.

Sharing ubiquitous mobile sensor data, especially physiological data, raises potential risks of leaking physical and demographic information that can be inferred from the time series sensor data. Existing sensitive information protection mechanisms that depend on data transformation are effective only on a particular sensitive attribute, together with usually requiring the labels of sensitive information for training. Considering this gap, we propose a novel user sensitive information protection framework without using a sensitive training dataset or being validated on protecting only one specific sensitive information. The presented approach transforms raw sensor data into a new format that has a "style" (sensitive information) of random noise and a "content" (desired information) of the raw sensor data, thus is free of user sensitive information for training and able to collectively protect all sensitive information at once. Our implementation and experiments on two real-world multisensor human activity datasets demonstrate that the proposed data transformation technique can achieve the protection for all sensitive information at once without requiring the knowledge of users' personal attributes for training, and simultaneously preserve the usability of the new transformed data with regard to inferring human activities with insignificant performance loss.

A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototype propagation network (PPN) trained on few-shot tasks together with data annotated by coarse-label. Given a category graph of the targeted fine-classes and some weakly-labeled coarse-classes, PPN learns an attention mechanism which propagates the prototype of one class to another on the graph, so that the K-nearest neighbor (KNN) classifier defined on the propagated prototypes results in high accuracy across different few-shot tasks. The training tasks are generated by subgraph sampling, and the training objective is obtained by accumulating the level-wise classification loss on the subgraph. On two benchmarks, PPN significantly outperforms most recent few-shot learning methods in different settings, even when they are also allowed to train on weakly-labeled data.

Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step frameworks are difficult to manipulate and usually lead to suboptimal performance, mainly because the graph embedding is not goal-directed, i.e., designed for the specific clustering task. In this paper, we propose a goal-directed deep learning approach, Deep Attentional Embedded Graph Clustering (DAEGC for short). Our method focuses on attributed graphs to sufficiently explore the two sides of information in graphs. By employing an attention network to capture the importance of the neighboring nodes to a target node, our DAEGC algorithm encodes the topological structure and node content in a graph to a compact representation, on which an inner product decoder is trained to reconstruct the graph structure. Furthermore, soft labels from the graph embedding itself are generated to supervise a self-training graph clustering process, which iteratively refines the clustering results. The self-training process is jointly learned and optimized with the graph embedding in a unified framework, to mutually benefit both components. Experimental results compared with state-of-the-art algorithms demonstrate the superiority of our method.

Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, {Graph WaveNet}, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.

Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. At present, the vast majority of GCNs use a neighborhood aggregation framework to learn a continuous and compact vector, then performing a pooling operation to generalize graph embedding for the classification task. These approaches have two disadvantages in the graph classification task: (1)when only the largest sub-graph structure (k-hop neighbor) is used for neighborhood aggregation, a large amount of early-stage information is lost during the graph convolution step; (2) simple average/sum pooling or max pooling utilized, which loses the characteristics of each node and the topology between nodes. In this paper, we propose a novel framework called, dual attention graph convolutional networks (DAGCN) to address these problems. DAGCN automatically learns the importance of neighbors at different hops using a novel attention graph convolution layer, and then employs a second attention component, a self-attention pooling layer, to generalize the graph representation from the various aspects of a matrix graph embedding. The dual attention network is trained in an end-to-end manner for the graph classification task. We compare our model with state-of-the-art graph kernels and other deep learning methods. The experimental results show that our framework not only outperforms other baselines but also achieves a better rate of convergence.

Mobile keyboard suggestion is typically regarded as a word-level language modeling problem. Centralized machine learning techniques require the collection of massive user data for training purposes, which may raise privacy concerns in relation to users' sensitive data. Federated learning (FL) provides a promising approach to learning private language modeling for intelligent personalized keyboard suggestions by training models on distributed clients rather than training them on a central server. To obtain a global model for prediction, existing FL algorithms simply average the client models and ignore the importance of each client during model aggregation. Furthermore, there is no optimization for learning a well-generalized global model on the central server. To solve these problems, we propose a novel model aggregation with an attention mechanism considering the contribution of client models to the global model, together with an optimization technique during server aggregation. Our proposed attentive aggregation method minimizes the weighted distance between the server model and client models by iteratively updating parameters while attending to the distance between the server model and client models. Experiments on two popular language modeling datasets and a social media dataset show that our proposed method outperforms its counterparts in terms of perplexity and communication cost in most settings of comparison.

Electronic health records contain a wealth of information on a patients healthcare over many visits, such as diagnoses, treatments, drugs administered, and so on. The untapped potential of these data in healthcare analytics is vast. However, given that much of medical information is a cause and effect science, new embedding methods are required to ensure the learning representations reflect the comprehensive interplays between medical concepts and their relationships over time. Unlike one-hot encoding, a distributed representation should preserve these complex interactions as high-quality inputs for machine learning-based healthcare analytics tasks. Therefore, we propose a novel attentive dual embedding method called MC2Vec. MC2Vec captures the proximity relationships between medical concepts through a two-step optimization framework that recursively refines the embedding for superior output. The framework comprises a Skip-gram model to generate the initial embedding and an attentive CBOW model to fine-tune the embedding with temporal information gleaned from sequences of patient visits. Experiments with two public datasets demonstrate that MC2Vecs produces embeddings of higher quality than five state-of-the-art methods.

Human gestures are unique for recognizing and describing human actions, and video-based human action recognition techniques are effective solutions to varies real-world applications, such as surveillance, video indexing, and human-computer interaction. Most existing video human action recognition approaches either using handcraft features from the frames or deep learning models such as convolutional neural networks (CNN) and recurrent neural networks (RNN); however, they have mostly overlooked the similar gestures between different actions when processing the frames into the models. The classifiers suffer from similar features extracted from similar gestures, which are unable to classify the actions in the video streams. In this paper, we propose a novel framework with generative adversarial networks (GAN) to generate the data augmentation for similar gesture action recognition. The contribution of our work is tri-fold: 1) we proposed a novel action data augmentation framework (ADAF) to enlarge the differences between the actions with very similar gestures; 2) the framework can boost the classification performance either on similar gesture action pairs or the whole dataset; 3) experiments conducted on both KTH and UCF101 datasets show that our data augmentation framework boost the performance on both similar gestures actions as well as the whole dataset compared with baseline methods such as 2DCNN and 3DCNN.

Meta-learning extracts the common knowledge from learning different tasks and uses it for unseen tasks. It can significantly improve tasks that suffer from insufficient training data, e.g., few-shot learning. In most meta-learning methods, tasks are implicitly related by sharing parameters or optimizer. In this paper, we show that a meta-learner that explicitly relates tasks on a graph describing the relations of their output dimensions (e.g., classes) can significantly improve few-shot learning. The graph’s structure is usually free or cheap to obtain but has rarely been explored in previous works. We develop a novel meta-learner of this type for prototype based classification, in which a prototype is generated for each class, such that the nearest neighbor search among the prototypes produces an accurate classification. The meta-learner, called “Gated Propagation Network (GPN)”, learns to propagate messages between prototypes of different classes on the graph, so that learning the prototype of each class benefits from the data of other related classes. In GPN, an attention mechanism aggregates messages from neighboring classes of each class, with a gate choosing between the aggregated message and the message from the class itself. We train GPN on a sequence of tasks from many-shot to few-shot generated by subgraph sampling. During training, it is able to reuse and update previously achieved prototypes from the memory in a life-long learning cycle. In experiments, under different training-test discrepancy and test task generation settings, GPN outperforms recent meta-learning methods on two benchmark datasets. Code of GPN is publicly available at: https://github.com/liulu112601/Gated-Propagation-Net.

Time series has been a popular research topic over the past decade. Salient subsequences of time series that can benefit the learning task, e.g., classification or clustering, are called shapelets. Shapelet-based time series learning extracts these types of salient subsequences with highly informative features from a time series. Most existing methods for shapelet discovery must scan a large pool of candidate subsequences, which is a time-consuming process. A recent work, [1] , uses regression learning to discover shapelets in a time series; however, it only considers learning shapelets from labeled time series data. This paper proposes an Unsupervised Salient Subsequence Learning (USSL) model that discovers shapelets without the effort of labeling. We developed this new learning function by integrating the strengths of shapelet learning, shapelet regularization, spectral analysis and pseudo-label to simultaneously and automatically learn shapelets to help clustering unlabeled time series better. The optimization model is iteratively solved via a coordinate descent algorithm. Experiments show that our USSL can learn meaningful shapelets, with promising results on real-world and synthetic data that surpass current state-of-the-art unsupervised time series learning methods.

Fisher's linear discriminant analysis is a widely accepted dimensionality reduction method, which aims to find a transformation matrix to convert feature space to a smaller space by maximising the between-class scatter matrix while minimising the within-class scatter matrix. Although the fast and easy process of finding the transformation matrix has made this method attractive, overemphasizing the large class distances makes the criterion of this method suboptimal. In this case, the close class pairs tend to overlap in the subspace. Despite different weighting methods having been developed to overcome this problem, there is still a room to improve this issue. In this work, we study a weighted trace ratio by maximising the harmonic mean of the multiple objective reciprocals. To further improve the performance, we enforce the l2,1-norm to the developed objective function. Additionally, we propose an iterative algorithm to optimise this objective function. The proposed method avoids the domination problem of the largest objective, and guarantees that no objectives will be too small. This method can be more beneficial if the number of classes is large. The extensive experiments on different datasets show the effectiveness of our proposed method when compared with four state-of-the-art methods.

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the attention between elements from input sequence(s) is directional and multi-dimensional (i.e., feature-wise). A light-weight neural net, "Directional Self-Attention Network (DiSAN)," is then proposed to learn sentence embedding, based solely on the proposed attention without any RNN/CNN structure. DiSAN is only composed of a directional self-attention with temporal order encoded, followed by a multi-dimensional attention that compresses the sequence into a vector representation. Despite its simple form, DiSAN outperforms complicated RNN models on both prediction quality and time efficiency. It achieves the best test accuracy among all sentence encoding methods and improves the most recent best result by 1.02% on the Stanford Natural Language Inference (SNLI) dataset, and shows state-of-the-art test accuracy on the Stanford Sentiment Treebank (SST), Multi-Genre natural language inference (MultiNLI), Sentences Involving Compositional Knowledge (SICK), Customer Review, MPQA, TREC question-type classification and Subjectivity (SUBJ) datasets.

Most of the existing analytics on ICU data mainly focus on mortality risk prediction and phenotyping analysis. However, they have limitations in providing sufficient evidence for decision making in a dynamically changing clinical environment. In this paper, we propose a novel approach that simultaneously analyses different organ systems to predict the illness severity of patients in an ICU, which can intuitively reflect the condition of the patients in a timely fashion. Specifically, we develop a novel deep learning model, namely MTRNN-ATT, which is based on multi-task recurrent neural networks. The physiological features of each organ system in time-series representations are learned by a single long short-term memory unit as a specific task. To utilize the relationships between organ systems, we use a shared LSTM unit to exploit the correlations between different tasks for further performance improvement. Also, we apply an attention mechanism in our deep model to learn the selective features at each stage to achieve better prediction results. We conduct extensive experiments on a real-world clinical dataset (MIMIC-III) to compare our method with many state-of-the-art methods. The experiment results demonstrate that the proposed approach performs better on the prediction tasks of illness severity scores.

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.

Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two tokens, but they are not effective and efficient when applied to long sentences. By contrast, hard attention mechanisms directly select a subset of tokens but are difficult and inefficient to train due to their combinatorial nature. In this paper, we integrate both soft and hard attention into one context fusion model, "reinforced self-attention (ReSA)", for the mutual benefit of each other. In ReSA, a hard attention trims a sequence for a soft self-attention to process, while the soft attention feeds reward signals back to facilitate the training of the hard one. For this purpose, we develop a novel hard attention called "reinforced sequence sampling (RSS)", selecting tokens in parallel and trained via policy gradient. Using two RSS modules, ReSA efficiently extracts the sparse dependencies between each pair of selected tokens. We finally propose an RNN/CNN-free sentence-encoding model, "reinforced self-attention network (ReSAN)", solely based on ReSA. It achieves state-of-the-art performance on both the Stanford Natural Language Inference (SNLI) and the Sentences Involving Compositional Knowledge (SICK) datasets.

Multimodel wearable sensor data classificationplays an important role in ubiquitous computingand has a wide range of applications in variousscenarios from healthcare to entertainment. How-ever, most of the existing work in this field em-ploys domain-specific approaches and is thus inef-fective in complex situations where multi-modalitysensor data is collected. Moreover, the wearablesensor data is less informative than the conven-tional data such as texts or images. In this paper,to improve the adaptability of such classificationmethods across different application contexts, weturn this classification task into a game and applya deep reinforcement learning scheme to dynami-cally deal with complex situations. We also intro-duce a selective attention mechanism into the rein-forcement learning scheme to focus on the crucialdimensions of the data. This mechanism helps tocapture extra information from the signal, and canthus significantly improve the discriminative powerof the classifier. We carry out several experimentson three wearable sensor datasets, and demonstratecompetitive performance of the proposed approachcompared to several state-of-the-art baselines.

Modeling user-item interaction patterns is an important task for personalized recommendations. Many recommender systems are based on the assumption that there exists a linear relationship between users and items while neglecting the intricacy and non-linearity of real-life historical interactions. In this paper, we propose a neural network based recommendation model (NeuRec) that untangles the complexity of user-item interactions and establish an integrated network to combine non-linear transformation with latent factors. We further design two variants of NeuRec: user-based NeuRec and item-based NeuRec, by focusing on different aspects of the interaction matrix. Extensive experiments on four real-world datasets demonstrated their superior performances on personalized ranking task.

Over recent decades, globalization has resulted in a steady increase in cross-border financial flows around the world. To build an abstract representation of a real-world financial market situation, we structure the fundamental influences among homogeneous and heterogeneous markets with three types of correlations: the inner-domain correlation between homogeneous markets in various countries, the cross-domain correlation between heterogeneous markets, and the time-series correlation between current and past markets. Such types of correlations in global finance challenge traditional machine learning approaches due to model complexity and nonlinearity. In this paper, we propose a novel cross-domain deep learning approach (Cd-DLA) to learn real-world complex correlations for multiple financial market prediction. Based on recurrent neural networks, which capture the time-series interactions in financial data, our model utilizes the attention mechanism to analyze the inner-domain and cross-domain correlations, and then aggregates all of them for financial forecasting. Experiment results on ten-year financial data on currency and stock markets from three countries prove the performance of our approach over other baselines.

Analyzing accumulated data has recently attracted huge attention for its ability to generate values by identifying useful information and providing an edge in global business competition. However, heterogeneous data and imbalanced class distribution present two major challenges to machine learning with real-world business data. Traditional machine learning algorithms can typically only be applied to standard data sets, which are normally homogeneous and balanced. These algorithms narrow complex data into a homogeneous, a balanced data space an inefficient process that requires a significant amount of pre-processing. In this paper, we focus on an efficient solution to the challenges with heterogeneous and imbalanced data sets that does not require pre-processing. Our approach comprises a novel, unified, end-to-end cost-sensitive hybrid neural network that learns real-world heterogeneous data via a parallel network architecture. A specifically-designed cost-sensitive matrix then automatically generates a robust model for learning minority classifications. And the parameters of both the cost-sensitive matrix and the hybrid neural network are alternately but jointly optimized during training. The results of comparative experiments on six real-world data sets reflecting actual business cases, including insurance fraud detection and mobile customer demographics, indicate that the proposed approach demonstrates superior performance over baseline procedures.

Numerous network representation-based algorithms for network classification have emerged in recent years, but many suffer from two limitations. First, they separate the network representation learning and node classification in networks into two steps, which may result in sub-optimal results because the node representation may not fit the classification model well, and vice versa. Second, they are mostly shallow methods that can only capture the linear and simple relationships in the data. In this paper, we propose an effective deep learning model, Graph Ladder Networks (GLN), for node classification in networks. Our model learns a ladder network which unifies the representation learning and network classification into one single framework by exploiting both labeled and unlabeled nodes in a network. To integrate both structure and node content information in the networks, the most recently developed graph convolution network, is further employed. The experiments on the most popular academic network dataset, Citeseer, demonstrate that our approach reaches outstanding performance compared to other state-of-the-art algorithms.

Graph clustering aims to discovercommunity structures in networks, the task being fundamentally challenging mainly because the topology structure and the content of the graphs are difficult to represent for clustering analysis. Recently, graph clustering has moved from traditional shallow methods to deep learning approaches, thanks to the unique feature representation learning capability of deep learning. However, existing deep approaches for graph clustering can only exploit the structure information, while ignoring the content information associated with the nodes in a graph. In this paper, we propose a novel marginalized graph autoencoder (MGAE) algorithm for graph clustering. The key innovation of MGAE is that it advances the autoencoder to the graph domain, so graph representation learning can be carried out not only in a purely unsupervised setting by leveraging structure and content information, it can also be stacked in a deep fashion to learn effective representation. From a technical viewpoint, we propose a marginalized graph convolutional network to corrupt network node content, allowing node content to interact with network features, and marginalizes the corrupted features in a graph autoencoder context to learn graph feature representations. The learned features are fed into the spectral clustering algorithm for graph clustering. Experimental results on benchmark datasets demonstrate the superior performance of MGAE, compared to numerous baselines.

Network representation aims to represent the nodes in a network as continuous and compact vectors, and has attracted much attention in recent years due to its ability to capture complex structure relationships inside networks. However, existing network representation methods are commonly designed for homogeneous information networks where all the nodes (entities) of a network are of the same type, e.g., papers in a citation network. In this paper, we propose a universal network representation approach (UNRA), that represents different types of nodes in heterogeneous information networks in a continuous and common vector space. The UNRA is built on our latest mutually updated neural language module, which simultaneously captures inter-relationship among homogeneous nodes and node-content correlation. Relationships between different types of nodes are also assembled and learned in a unified framework. Experiments validate that the UNRA achieves outstanding performance, compared to six other state-of-the-art algorithms, in node representation, node classification, and network visualization. In node classification, the UNRA achieves a 3% to 132% performance improvement in terms of accuracy.

Multitask learning (MTL) is commonly used for jointly optimizing multiple learning tasks. To date, all existing MTL methods have been designed for tasks with feature-vector represented instances, but cannot be applied to structure data, such as graphs. More importantly, when carrying out MTL, existing methods mainly focus on exploring overall commonality or disparity between tasks for learning, but cannot explicitly capture task relationships in the feature space, so they are unable to answer important questions, such as what exactly is shared between tasks and what is the uniqueness of one task differing from others? In this paper, we formulate a new multitask graph learning problem, and propose a task sensitive feature exploration and learning algorithm for multitask graph classification. Because graphs do not have features available, we advocate a task sensitive feature exploration and learning paradigm to jointly discover discriminative subgraph features across different tasks. In addition, a feature learning process is carried out to categorize each subgraph feature into one of three categories: (1) common feature; (2) task auxiliary feature; and (3) task specific feature, indicating whether the feature is shared by all tasks, by a subset of tasks, or by only one specific task, respectively. The feature learning and the multiple task learning are iteratively optimized to form a multitask graph classification model with a global optimization goal. Experiments on real-world functional brain analysis and chemical compound categorization demonstrate the algorithm's performance. Results confirm that our method can be used to explicitly capture task correlations and uniqueness in the feature space, and explicitly answer what are shared between tasks and what is the uniqueness of a specific task.

In the era of big data, a mechanism that can automatically annotate disease codes to patients’ records in the medical information system is in demand. The purpose of this work is to propose a framework that automatically annotates the disease labels of multi-source patient data in Intensive Care Units (ICUs). We extract features from two main sources, medical charts and notes. The Bag-of-Words model is used to encode the features. Unlike most of the existing multi-label learning algorithms that globally consider correlations between diseases, our model learns disease correlation locally in the patient data. To achieve this, we derive a local disease correlation representation to enrich the discriminant power of each patient data. This representation is embedded into a unified multi-label learning framework. We develop an alternating algorithm to iteratively optimize the objective function. Extensive experiments have been conducted on a real-world ICU database. We have compared our algorithm with representative multi-label learning algorithms. Evaluation results have shown that our proposed method has state-of-the-art performance in the annotation of multiple diagnostic codes for ICU patients. This study suggests that problems in the automated diagnosis code annotation can be reliably addressed by using a multi-label learning model that exploits disease correlation. The findings of this study will greatly benefit health care and management in ICU considering that the automated diagnosis code annotation can significantly improve the quality and management of health care for both patients and caregivers.

In this paper, we focus on automatically detecting events in unconstrained videos without the use of any visual training exemplars. In principle, zero-shot learning makes it possible to train an event detection model based on the assumption that events (e.g. birthday party) can be described by multiple mid-level semantic concepts (e.g. ``blowing candle'', ``birthday cake''). Towards this goal, we first pre-train a bundle of concept classifiers using data from other sources. Then we evaluate the semantic correlation of each concept w.r.t. the event of interest and pick up the relevant concept classifiers, which are applied on all test videos to get multiple prediction score vectors. While most existing systems combine the predictions of the concept classifiers with fixed weights, we propose to learn the optimal weights of the concept classifiers for each testing video by exploring a set of online available videos with free-form text descriptions of their content. To validate the effectiveness of the proposed approach, we have conducted extensive experiments on the latest TRECVID MEDTest 2014, MEDTest 2013 and CCV dataset. The experimental results confirm the superiority of the proposed approach.

Semi-supervised learning is proposed to exploit both labeled and unlabeled data. However, as the scale of data in real world applications increases significantly, conventional semi-supervised algorithms usually lead to massive computational cost and cannot be applied to large scale datasets. In addition, label noise is usually present in the practical applications due to human annotation, which very likely results in remarkable degeneration of performance in semi-supervised methods. To address these two challenges, in this paper, we propose an efficient RObust Semi-Supervised Ensemble Learning (ROSSEL) method, which generates pseudo-labels for unlabeled data using a set of weak annotators, and combines them to approximate the ground-truth labels to assist semi-supervised learning. We formulate the weighted combination process as a multiple label kernel learning (MLKL) problem which can be solved efficiently. Compared with other semi-supervised learning algorithms, the proposed method has linear time complexity. Extensive experiments on five benchmark datasets demonstrate the superior effectiveness, efficiency and robustness of the proposed algorithm.

Social recommendation has been widely studied in recent years. Existing social recommendation models use various explicit pieces of social information as regularization terms in recommendation, for instance, social links are considered as new constraints. However, social influence, an implicit source of information in social networks, is seldomly considered, even though it often drives recommendations in social networks. In this paper, we introduce a new global and local influence-based social recommendation model. Based on the observation that user purchase behaviour is influenced by both global influential nodes and the local influential nodes of the user, we formulate the global and local influence as an regularization terms, and incorporate them into a matrix factorization-based recommendation model. Experimental results on large data sets demonstrate the performance of the proposed method.

Social recommendation explores social information to improve the quality of a recommender system. It can be further divided into explicit and implicit social network recommendation. The former assumes the existence of explicit social connections between users in addition to the rating data. The latter one assumes the availability of only the ratings but not the social connections between users since the explicit social information data may not necessarily be available and usually are binary decision values (e.g., whether two people are friends), while the strength of their relationships is missing. Most of the works in this field use only rating data to infer the latent social networks. They ignore the dynamic nature of users that the preferences of users drift over time distinctly. To this end, we propose a new Implicit Dynamic Social Recommendation (IDSR) model, which infers latent social network from cascade data. It can sufficiently mine the information contained in time by mining the cascade data and identify the dynamic changes in the users in time by using the latest updated social network to make recommendations. Experiments and comparisons on three real-world datasets show that the proposed model outperforms the state-of-the-art solutions in both explicit and implicit scenarios.

Most improvements for Naive Bayes (NB) have a common yet important flaw - these algorithms split the modeling of the classifier into two separate stages - the stage of preprocessing (e.g., feature selection and data expansion) and the stage of building the NB classifier. The first stage does not take the NB's objective function into consideration, so the performance of the classification cannot be guaranteed. Motivated by these facts and aiming to improve NB with accurate classification, we present a new learning algorithm called Evolutionary Local Instance Weighted Naive Bayes or ELWNB, to extend NB for classification. ELWNB combines local NB, instance weighted dataset extension and evolutionary algorithms seamlessly. Experiments on 20 UCI benchmark datasets demonstrate that ELWNB significantly outperforms NB and several other improved NB algorithms.

An enterprise social network (ESN) involves diversified user groups from producers, suppliers, logistics, to end consumers, and users have different scales, broad interests, and various objectives, such as advertising, branding, customer relationship management etc. In addition, such a highly diversified network is also featured with rich content, including recruiting messages, advertisements, news release, customer complains etc. Due to such complex nature, an immediate need is to properly organize a chaotic enterprise social network as functional groups, where each group corresponds to a set of peers with business interactions and common objectives, and further understand the business role of each group, such as their common interests and key features differing from other groups. In this paper, we argue that due to unique characteristics of enterprise social networks, simple clustering for ESN nodes or using existing topic discovery methods cannot effectively discover functional groups and understand their roles. Alternatively, we propose CENFLD, which carries out co-clustering on enterprise social networks for functional group discovery and understanding. CENFLD is a co-factorization based framework which combines network topology structures and rich content information, including interactions between nodes and correlations between node content, to discover functional user groups. Because the number of functional groups is highly data driven and hard to estimate, CENFLD employs a hold-out test principle to find the group number optimally complying with the underlying data. Experiments and comparisons, with state-of-the-art approaches, on 13 real-world enterprise/organizational networks validate the performance of CENFLD.

With the latest developments in database technologies, it becomes easier to store the medical records of hospital patients from their first day of admission than was previously possible. In Intensive Care Units (ICU), modern medical information systems can record patient events in relational databases every second. Knowledge mining from these huge volumes of medical data is beneficial to both caregivers and patients. Given a set of electronic patient records, a system that effectively assigns the disease labels can facilitate medical database management and also benefit other researchers, e.g., pathologists. In this paper, we have proposed a framework to achieve that goal. Medical chart and note data of a patient are used to extract distinctive features. To encode patient features, we apply a Bag-of-Words encoding method for both chart and note data. We also propose a model that takes into account both global information and local correlations between diseases. Correlated diseases are characterized by a graph structure that is embedded in our sparsity-based framework. Our algorithm captures the disease relevance when labeling disease codes rather than making individual decision with respect to a specific disease. At the same time, the global optimal values are guaranteed by our proposed convex objective function. Extensive experiments have been conducted on a real-world large-scale ICU database. The evaluation results demonstrate that our method improves multi-label classification results by successfully incorporating disease correlations.

In this paper, we study a new problem of continuous learning from doubly-streaming data where both data volume and feature space increase over time. We refer to the doubly-streaming data as trapezoidal data streams and the corresponding learning problem as online learning from trapezoidal data streams. The problem is challenging because both data volume and data dimension increase over time, and existing online learning[1],[2], online feature selection[3], and streaming feature selection algorithms[4],[5]are inapplicable. We propose a new Online Learning with Streaming Features algorithm (OL$_{SF}$for short) and its two variants, which combine online learning[1],[2]and streaming feature selection[4],[5]to enable learning from trapezoidal data streams with infinite training instances and features. When a new training instance carrying new features arrives, a classifier updates the existing features by following the passive-aggressive update rule[2]and updates the new features by following the structural risk minimization principle. Feature sparsity is then introduced by using the projected truncation technique. We derive performance bounds of the OL$_{SF}$algorithm and its variants. We also conduct experiments on real-world data sets to show the performance of the proposed algorithms.

Witnessing the wide spread of malicious information in large networks, we develop an efficient method to detect anomalous diffusion sources and thus protect networks from security and privacy attacks. To date, most existing work on diffusion sources detection are based on the assumption that network snapshots that reflect information diffusion can be obtained continuously. However, obtaining snapshots of an entire network needs to deploy detectors on all network nodes and thus is very expensive. Alternatively, in this article, we study the diffusion sources locating problem by learning from information diffusion data collected from only a small subset of network nodes. Specifically, we present a new regression learning model that can detect anomalous diffusion sources by jointly solving five challenges, that is, unknown number of source nodes, few activated detectors, unknown initial propagation time, uncertain propagation path and uncertain propagation time delay. We theoretically analyze the strength of the model and derive performance bounds. We empirically test and compare the model using both synthetic and real-world networks to demonstrate its performance.

Context-aware features have been widely recognized as important factors in recommender systems. However, as a major technique in recommender systems, traditional Collaborative Filtering (CF) does not provide a straight-forward way of integrating the context-aware information into personal recommendation. We propose a Coupled Collaborative Filtering (CCF) model to measure the contextual information and use it to improve recommendations. In the proposed approach, coupled similarity computation is designed to be calculated by interitem, intra-context and inter-context interactions among item, user and context-ware factors. Experiments based on different types of CF models demonstrate the effectiveness of our design.

We study a new problem of learning from doubly-streaming data where both data volume and feature space increase over time. We refer to the problem as mining trapezoidal data streams. The problem is challenging because both data volume and feature space are increasing, to which existing online learning, online feature selection and streaming feature selection algorithms are inapplicable. We propose a new Sparse Trapezoidal Streaming Data mining algorithm (STSD) and its two variants which combine online learning and online feature selection to enable learning trapezoidal data streams with infinite training instances and features. Specifically, when new training instances carrying new features arrive, the classifier updates the existing features by following the passive-aggressive update rule used in online learning and updates the new features with the structural risk minimization principle. Feature sparsity is also introduced using the projected truncation techniques. Extensive experiments on the demonstrated UCI data sets show the performance of the proposed algorithms.

In the on-demand cloud environment, web application providers have the potential to scale virtual resources up or down to achieve cost-effective outcomes. True elasticity and cost-effectiveness in the pay-per-use cloud business model, however, have not yet been achieved. To address this challenge, we propose a novel cloud resource auto-scaling scheme at the virtual machine (VM) level for web application providers. The scheme automatically predicts the number of web requests and discovers an optimal cloud resource demand with cost-latency trade-off. Based on this demand, the scheme makes a resource scaling decision that is up or down or NOP (no operation) in each time-unit re-allocation. We have implemented the scheme on the Amazon cloud platform and evaluated it using three real-world web log datasets. Our experiment results demonstrate that the proposed scheme achieves resource auto-scaling with an optimal cost-latency trade-off, as well as low SLA violations.

Short & sparse text is becoming more prevalent on the web, such as search snippets, micro-blogs and product reviews. Accurately classifying short & sparse text has emerged as an important while challenging task. Existing work has considered utilizing external data (e.g. Wikipedia) to alleviate data sparseness, by appending topics detected from external data as new features. However, training a classifier on features concatenated from different spaces is not easy considering the features have different physical meanings and different significance to the classification task. Moreover, it exacerbates the "curse of dimensionality" problem. In this study, we propose a transfer classification method, TCSST, to exploit the external data to tackle the data sparsity issue. The transfer classifier will be learned in the original feature space. Considering that the labels of the external data may not be readily available or sufficiently enough, TCSST further exploits the unlabeled external data to aid the transfer classification. We develop novel strategies to allow TCSST to iteratively select high quality unlabeled external data to help with the classification. We evaluate the performance of TCSST on both benchmark as well as real-world data sets. Our experimental results demonstrate that the proposed method is effective in classifying very short & sparse text, consistently outperforming existing and baseline methods.

Collaborative filtering (CF) techniques have achieved widespread success in E-commerce nowadays. The tremendous growth of the number of customers and products in recent years poses some key challenges for recommender systems in which high quality recommendations are required and more recommendations per second for millions of customers and products need to be performed. Thus, the improvement of scalability and efficiency of collaborative filtering (CF) algorithms become increasingly important and difficult. In this paper, we developed and implemented a scaling-up item-based collaborative filtering algorithm on MapReduce, by splitting the three most costly computations in the proposed algorithm into four Map-Reduce phases, each of which can be independently executed on different nodes in parallel. We also proposed efficient partition strategies not only to enable the parallel computation in each Map-Reduce phase but also to maximize data locality to minimize the communication cost. Experimental results effectively showed the good performance in scalability and efficiency of the item-based CF algorithm on a Hadoop cluster.