Recent studies reveal that various biases exist in different NLP tasks, and over-reliance on biases results in models' poor generalization ability and low adversarial robustness. To mitigate datasets biases, previous works propose lots of debiasing techniques to tackle specific biases, which perform well on respective adversarial sets but fail to mitigate other biases. In this paper, we propose a new debiasing method Sparse Mixture-of-Adapters (SMoA), which can mitigate multiple dataset biases effectively and efficiently. Experiments on Natural Language Inference and Paraphrase Identification tasks demonstrate that SMoA outperforms full-finetuning, adapter tuning baselines, and prior strong debiasing methods. Further analysis indicates the interpretability of SMoA that sub-adapter can capture specific pattern from the training data and specialize to handle specific bias.
Graph, such as citation networks, social networks, and transportation networks, are prevalent in the real world. Graph Neural Networks (GNNs) have gained widespread attention for their robust expressiveness and exceptional performance in various graph applications. However, the efficacy of GNNs is heavily reliant on sufficient data labels and complex network models, with the former obtaining hardly and the latter computing costly. To address the labeled data scarcity and high complexity of GNNs, Knowledge Distillation (KD) has been introduced to enhance existing GNNs. This technique involves transferring the soft-label supervision of the large teacher model to the small student model while maintaining prediction performance. This survey offers a comprehensive overview of Graph-based Knowledge Distillation methods, systematically categorizing and summarizing them while discussing their limitations and future directions. This paper first introduces the background of graph and KD. It then provides a comprehensive summary of three types of Graph-based Knowledge Distillation methods, namely Graph-based Knowledge Distillation for deep neural networks (DKD), Graph-based Knowledge Distillation for GNNs (GKD), and Self-Knowledge Distillation based Graph-based Knowledge Distillation (SKD). Each type is further divided into knowledge distillation methods based on the output layer, middle layer, and constructed graph. Subsequently, various algorithms' ideas are analyzed and compared, concluding with the advantages and disadvantages of each algorithm supported by experimental results. In addition, the applications of graph-based knowledge distillation in CV, NLP, RS, and other fields are listed. Finally, the graph-based knowledge distillation is summarized and prospectively discussed. We have also released related resources at https://github.com/liujing1023/Graph-based-Knowledge-Distillation.
With the rapid development of intelligent transportation system applications, a tremendous amount of multi-view video data has emerged to enhance vehicle perception. However, performing video analytics efficiently by exploiting the spatial-temporal redundancy from video data remains challenging. Accordingly, we propose a novel traffic-related framework named CEVAS to achieve efficient object detection using multi-view video data. Briefly, a fine-grained input filtering policy is introduced to produce a reasonable region of interest from the captured images. Also, we design a sharing object manager to manage the information of objects with spatial redundancy and share their results with other vehicles. We further derive a content-aware model selection policy to select detection methods adaptively. Experimental results show that our framework significantly reduces response latency while achieving the same detection accuracy as the state-of-the-art methods.
Avatar creation from human images allows users to customize their digital figures in different styles. Existing rendering systems like Bitmoji, MetaHuman, and Google Cartoonset provide expressive rendering systems that serve as excellent design tools for users. However, twenty-plus parameters, some including hundreds of options, must be tuned to achieve ideal results. Thus it is challenging for users to create the perfect avatar. A machine learning model could be trained to predict avatars from images, however the annotators who label pairwise training data have the same difficulty as users, causing high label noise. In addition, each new rendering system or version update requires thousands of new training pairs. In this paper, we propose a Tag-based annotation method for avatar creation. Compared to direct annotation of labels, the proposed method: produces higher annotator agreements, causes machine learning to generates more consistent predictions, and only requires a marginal cost to add new rendering systems.
Video Anomaly Event Detection (VAED) is the core technology of intelligent surveillance systems aiming to temporally or spatially locate anomalous events in videos. With the penetration of deep learning, the recent advances in VAED have diverged various routes and achieved significant success. However, most existing reviews focus on traditional and unsupervised VAED methods, lacking attention to emerging weakly-supervised and fully-unsupervised routes. Therefore, this review extends the narrow VAED concept from unsupervised video anomaly detection to Generalized Video Anomaly Event Detection (GVAED), which provides a comprehensive survey that integrates recent works based on different assumptions and learning frameworks into an intuitive taxonomy and coordinates unsupervised, weakly-supervised, fully-unsupervised, and supervised VAED routes. To facilitate future researchers, this review collates and releases research resources such as datasets, available codes, programming tools, and literature. Moreover, this review quantitatively compares the model performance and analyzes the research challenges and possible trends for future work.
Recent advances in Transformers have come with a huge requirement on computing resources, highlighting the importance of developing efficient training techniques to make Transformer training faster, at lower cost, and to higher accuracy by the efficient use of computation and memory resources. This survey provides the first systematic overview of the efficient training of Transformers, covering the recent progress in acceleration arithmetic and hardware, with a focus on the former. We analyze and compare methods that save computation and memory costs for intermediate tensors during training, together with techniques on hardware/algorithm co-design. We finally discuss challenges and promising areas for future research.
Robotic shepherding is a bio-inspired approach to autonomously guiding a swarm of agents towards a desired location and has earned increasing research interest recently. However, shepherding a highly dispersed swarm in an obstructive environment remains challenging for the existing methods. To improve the shepherding efficacy in complex environments with obstacles and dispersed sheep, this paper proposes a planning-assisted autonomous shepherding framework with collision avoidance. The proposed approach transforms the swarm shepherding problem into a single Travelling Salesman Problem (TSP), with the sheepdog moving mode classified into non-interaction and interaction mode. Additionally, an adaptive switching approach is integrated into the framework to guide real-time path planning for avoiding collisions with obstacles and sometimes with sheep swarm. Then the overarching hierarchical mission planning system is presented, which consists of a grouping approach to obtain sheep sub-swarms, a general TSP solver for determining the optimal push sequence of sub-swarms, and an online path planner for calculating optimal paths for both sheepdogs and sheep. The experiments on a range of environments, both with and without obstacles, quantitatively demonstrate the effectiveness of the proposed shepherding framework and planning approaches.
Discovering the governing equations of evolving systems from available observations is essential and challenging. However, current methods does not capture the situation that underlying system dynamics can be changed.Evolving systems are changing over time, which invariably changes with system status. Thus, finding the exact change points is critical. We propose an online modeling method capable of handling samples one by one sequentially by modeling streaming data instead of processing the entire dataset. The proposed method performs well in discovering ordinary differential equations, partial differential equations (PDEs), and high-dimensional PDEs from streaming data. The measurement generated from a changed system is distributed dissimilarly to before; hence, the difference can be identified by the proposed method. Our proposal performs well in identifying the change points and discovering governing differential equations in two evolving systems.
Compared to passive intelligent reflecting surface (IRS), active IRS is viewed as a more efficient promising technique to combat the double-fading impact in IRS-aided wireless network. In this paper, in order to boost the achievable rate of user in such a wireless network, three enhanced-rate iterative beamforming methods are proposed by designing the amplifying factors and the corresponding phases at active IRS. The first method, called generalized maximum ratio reflection (GMRR), is presented with a closed-form expression, which is motivated by the maximum ratio combing. To further improve rate, maximize the simplified signal-to-noise ratio (Max-SSNR) is designed by omitting the cross-term in the definition of rate. Using the Rayleigh-Ritz (RR) theorem and the fractional programming (FP), two enhanced methods, Max-SSNR-RR and Max-SSNR-FP are proposed to iteratively optimize the norm of beamforming vector and its associated normalized vector. Simulation results indicate that the proposed three methods make an obvious rate enhancement over Max-reflecting signal-to-noise ratio (RSNR) and passive IRS, and are in increasing order of rate performance as follows: GMRR, Max-SSNR-RR, and Max-SSNR-FP.
Clustering has been extensively studied in centralized settings, but relatively unexplored in federated ones that data are distributed among multiple clients and can only be kept local at the clients. The necessity to invest more resources in improving federated clustering methods is twofold: 1) The performance of supervised federated learning models can benefit from clustering. 2) It is non-trivial to extend centralized ones to perform federated clustering tasks. In centralized settings, various deep clustering methods that perform dimensionality reduction and clustering jointly have achieved great success. To obtain high-quality cluster information, it is natural but non-trivial to extend these methods to federated settings. For this purpose, we propose a simple but effective federated deep clustering method. It requires only one communication round between the central server and clients, can run asynchronously, and can handle device failures. Moreover, although most studies have highlighted adverse effects of the non-independent and identically distributed (non-IID) data across clients, experimental results indicate that the proposed method can significantly benefit from this scenario.