Anomaly detection in attributed networks has received a considerable attention in recent years due to its applications in a wide range of domains such as finance, network security, and medicine. Traditional approaches cannot be adopted on attributed networks' settings to solve the problem of anomaly detection. The main limitation of such approaches is that they inherently ignore the relational information between data features. With a rapid explosion in deep learning- and graph neural networks-based techniques, spotting rare objects on attributed networks has significantly stepped forward owing to the potentials of deep techniques in extracting complex relationships. In this paper, we propose a new architecture on anomaly detection. The main goal of designing such an architecture is to utilize multi-task learning which would enhance the detection performance. Multi-task learning-based anomaly detection is still in its infancy and only a few studies in the existing literature have catered to the same. We incorporate both community detection and multi-view representation learning techniques for extracting distinct and complementary information from attributed networks and subsequently fuse the captured information for achieving a better detection result. The mutual collaboration between two main components employed in this architecture, i.e., community-specific learning and multi-view representation learning, exhibits a promising solution to reach more effective results.
Conventional automatic speech recognition systems do not produce punctuation marks which are important for the readability of the speech recognition results. They are also needed for subsequent natural language processing tasks such as machine translation. There have been a lot of works on punctuation prediction models that insert punctuation marks into speech recognition results as post-processing. However, these studies do not utilize acoustic information for punctuation prediction and are directly affected by speech recognition errors. In this study, we propose an end-to-end model that takes speech as input and outputs punctuated texts. This model is expected to predict punctuation robustly against speech recognition errors while using acoustic information. We also propose to incorporate an auxiliary loss to train the model using the output of the intermediate layer and unpunctuated texts. Through experiments, we compare the performance of the proposed model to that of a cascaded system. The proposed model achieves higher punctuation prediction accuracy than the cascaded system without sacrificing the speech recognition error rate. It is also demonstrated that the multi-task learning using the intermediate output against the unpunctuated text is effective. Moreover, the proposed model has only about 1/7th of the parameters compared to the cascaded system.
Estimating dimensional emotions, such as activation, valence and dominance, from acoustic speech signals has been widely explored over the past few years. While accurate estimation of activation and dominance from speech seem to be possible, the same for valence remains challenging. Previous research has shown that the use of lexical information can improve valence estimation performance. Lexical information can be obtained from pre-trained acoustic models, where the learned representations can improve valence estimation from speech. We investigate the use of pre-trained model representations to improve valence estimation from acoustic speech signal. We also explore fusion of representations to improve emotion estimation across all three emotion dimensions: activation, valence and dominance. Additionally, we investigate if representations from pre-trained models can be distilled into models trained with low-level features, resulting in models with a less number of parameters. We show that fusion of pre-trained model embeddings result in a 79% relative improvement in concordance correlation coefficient CCC on valence estimation compared to standard acoustic feature baseline (mel-filterbank energies), while distillation from pre-trained model embeddings to lower-dimensional representations yielded a relative 12% improvement. Such performance gains were observed over two evaluation sets, indicating that our proposed architecture generalizes across those evaluation sets. We report new state-of-the-art "text-free" acoustic-only dimensional emotion estimation $CCC$ values on two MSP-Podcast evaluation sets.
The unbiased learning to rank (ULTR) problem has been greatly advanced by recent deep learning techniques and well-designed debias algorithms. However, promising results on the existing benchmark datasets may not be extended to the practical scenario due to the following disadvantages observed from those popular benchmark datasets: (1) outdated semantic feature extraction where state-of-the-art large scale pre-trained language models like BERT cannot be exploited due to the missing of the original text;(2) incomplete display features for in-depth study of ULTR, e.g., missing the displayed abstract of documents for analyzing the click necessary bias; (3) lacking real-world user feedback, leading to the prevalence of synthetic datasets in the empirical study. To overcome the above disadvantages, we introduce the Baidu-ULTR dataset. It involves randomly sampled 1.2 billion searching sessions and 7,008 expert annotated queries, which is orders of magnitude larger than the existing ones. Baidu-ULTR provides:(1) the original semantic feature and a pre-trained language model for easy usage; (2) sufficient display information such as position, displayed height, and displayed abstract, enabling the comprehensive study of different biases with advanced techniques such as causal discovery and meta-learning; and (3) rich user feedback on search result pages (SERPs) like dwelling time, allowing for user engagement optimization and promoting the exploration of multi-task learning in ULTR. In this paper, we present the design principle of Baidu-ULTR and the performance of benchmark ULTR algorithms on this new data resource, favoring the exploration of ranking for long-tail queries and pre-training tasks for ranking. The Baidu-ULTR dataset and corresponding baseline implementation are available at https://github.com/ChuXiaokai/baidu_ultr_dataset.
Recommender Systems (RS), as an efficient tool to discover users' interested items from a very large corpus, has attracted more and more attention from academia and industry. As the initial stage of RS, large-scale matching is fundamental yet challenging. A typical recipe is to learn user and item representations with a two-tower architecture and then calculate the similarity score between both representation vectors, which however still struggles in how to properly deal with negative samples. In this paper, we find that the common practice that randomly sampling negative samples from the entire space and treating them equally is not an optimal choice, since the negative samples from different sub-spaces at different stages have different importance to a matching model. To address this issue, we propose a novel method named Unbiased Model-Agnostic Matching Approach (UMA$^2$). It consists of two basic modules including 1) General Matching Model (GMM), which is model-agnostic and can be implemented as any embedding-based two-tower models; and 2) Negative Samples Debias Network (NSDN), which discriminates negative samples by borrowing the idea of Inverse Propensity Weighting (IPW) and re-weighs the loss in GMM. UMA$^2$ seamlessly integrates these two modules in an end-to-end multi-task learning framework. Extensive experiments on both real-world offline dataset and online A/B test demonstrate its superiority over state-of-the-art methods.
Text sentiment analysis, also known as opinion mining, is research on the calculation of people's views, evaluations, attitude and emotions expressed by entities. Text sentiment analysis can be divided into text-level sentiment analysis, sen-tence-level sentiment analysis and aspect-level sentiment analysis. Aspect-Based Sentiment Analysis (ABSA) is a fine-grained task in the field of sentiment analysis, which aims to predict the polarity of aspects. The research of pre-training neural model has significantly improved the performance of many natural language processing tasks. In recent years, pre training model (PTM) has been applied in ABSA. Therefore, there has been a question, which is whether PTMs contain sufficient syntactic information for ABSA. In this paper, we explored the recent DeBERTa model (Decoding-enhanced BERT with disentangled attention) to solve Aspect-Based Sentiment Analysis problem. DeBERTa is a kind of neural language model based on transformer, which uses self-supervised learning to pre-train on a large number of original text corpora. Based on the Local Context Focus (LCF) mechanism, by integrating DeBERTa model, we purpose a multi-task learning model for aspect-based sentiment analysis. The experiments result on the most commonly used the laptop and restaurant datasets of SemEval-2014 and the ACL twitter dataset show that LCF mechanism with DeBERTa has significant improvement.
Spatial reasoning poses a particular challenge for intelligent agents and is at the same time a prerequisite for their successful interaction and communication in the physical world. One such reasoning task is to describe the position of a target object with respect to the intrinsic orientation of some reference object via relative directions. In this paper, we introduce GRiD-A-3D, a novel diagnostic visual question-answering (VQA) dataset based on abstract objects. Our dataset allows for a fine-grained analysis of end-to-end VQA models' capabilities to ground relative directions. At the same time, model training requires considerably fewer computational resources compared with existing datasets, yet yields a comparable or even higher performance. Along with the new dataset, we provide a thorough evaluation based on two widely known end-to-end VQA architectures trained on GRiD-A-3D. We demonstrate that within a few epochs, the subtasks required to reason over relative directions, such as recognizing and locating objects in a scene and estimating their intrinsic orientations, are learned in the order in which relative directions are intuitively processed.
High-quality radio frequency (RF) components are imperative for efficient wireless communication. However, these components can degrade over time and need to be identified so that either they can be replaced or their effects can be compensated. The identification of these components can be done through observation and analysis of constellation diagrams. However, in the presence of multiple distortions, it is very challenging to isolate and identify the RF components responsible for the degradation. This paper highlights the difficulties of distorted RF components' identification and their importance. Furthermore, a deep multi-task learning algorithm is proposed to identify the distorted components in the challenging scenario. Extensive simulations show that the proposed algorithm can automatically detect multiple distorted RF components with high accuracy in different scenarios.
Voice Activity Detection (VAD) is an important pre-processing step in a wide variety of speech processing systems. VAD should in a practical application be able to detect speech in both noisy and noise-free environments, while not introducing significant latency. In this work we propose using an adversarial multi-task learning method when training a supervised VAD. The method has been applied to the state-of-the-art VAD Waveform-based Voice Activity Detection. Additionally the performance of the VADis investigated under different algorithmic delays, which is an important factor in latency. Introducing adversarial multi-task learning to the model is observed to increase performance in terms of Area Under Curve (AUC), particularly in noisy environments, while the performance is not degraded at higher SNR levels. The adversarial multi-task learning is only applied in the training phase and thus introduces no additional cost in testing. Furthermore the correlation between performance and algorithmic delays is investigated, and it is observed that the VAD performance degradation is only moderate when lowering the algorithmic delay from 398 ms to 23 ms.
Multitask learning is a framework that enforces multiple learning tasks to share knowledge to improve their generalization abilities. While shallow multitask learning can learn task relations, it can only handle predefined features. Modern deep multitask learning can jointly learn latent features and task sharing, but they are obscure in task relation. Also, they predefine which layers and neurons should share across tasks and cannot learn adaptively. To address these challenges, this paper proposes a new multitask learning framework that jointly learns latent features and explicit task relations by complementing the strength of existing shallow and deep multitask learning scenarios. Specifically, we propose to model the task relation as the similarity between task input gradients, with a theoretical analysis of their equivalency. In addition, we innovatively propose a multitask learning objective that explicitly learns task relations by a new regularizer. Theoretical analysis shows that the generalizability error has been reduced thanks to the proposed regularizer. Extensive experiments on several multitask learning and image classification benchmarks demonstrate the proposed method effectiveness, efficiency as well as reasonableness in the learned task relation patterns.
This paper describes the fourth Affective Behavior Analysis in-the-wild (ABAW) Competition, held in conjunction with European Conference on Computer Vision (ECCV), 2022. The 4th ABAW Competition is a continuation of the Competitions held at IEEE CVPR 2022, ICCV 2021, IEEE FG 2020 and IEEE CVPR 2017 Conferences, and aims at automatically analyzing affect. In the previous runs of this Competition, the Challenges targeted Valence-Arousal Estimation, Expression Classification and Action Unit Detection. This year the Competition encompasses two different Challenges: i) a Multi-Task-Learning one in which the goal is to learn at the same time (i.e., in a multi-task learning setting) all the three above mentioned tasks; and ii) a Learning from Synthetic Data one in which the goal is to learn to recognise the basic expressions from artificially generated data and generalise to real data. The Aff-Wild2 database is a large scale in-the-wild database and the first one that contains annotations for valence and arousal, expressions and action units. This database is the basis for the above Challenges. In more detail: i) s-Aff-Wild2 -- a static version of Aff-Wild2 database -- has been constructed and utilized for the purposes of the Multi-Task-Learning Challenge; and ii) some specific frames-images from the Aff-Wild2 database have been used in an expression manipulation manner for creating the synthetic dataset, which is the basis for the Learning from Synthetic Data Challenge. In this paper, at first we present the two Challenges, along with the utilized corpora, then we outline the evaluation metrics and finally present the baseline systems per Challenge, as well as their derived results. More information regarding the Competition can be found in the competition's website: https://ibug.doc.ic.ac.uk/resources/eccv-2023-4th-abaw/.
Zero-shot learning (ZSL) aims to predict unseen classes whose samples have never appeared during training. One of the most effective and widely used semantic information for zero-shot image classification are attributes which are annotations for class-level visual characteristics. However, the current methods often fail to discriminate those subtle visual distinctions between images due to not only the shortage of fine-grained annotations, but also the attribute imbalance and co-occurrence. In this paper, we present a transformer-based end-to-end ZSL method named DUET, which integrates latent semantic knowledge from the pre-trained language models (PLMs) via a self-supervised multi-modal learning paradigm. Specifically, we (1) developed a cross-modal semantic grounding network to investigate the model's capability of disentangling semantic attributes from the images; (2) applied an attribute-level contrastive learning strategy to further enhance the model's discrimination on fine-grained visual characteristics against the attribute co-occurrence and imbalance; (3) proposed a multi-task learning policy for considering multi-model objectives. We find that our DUET can achieve state-of-the-art performance on three standard ZSL benchmarks and a knowledge graph equipped ZSL benchmark. Its components are effective and its predictions are interpretable.
As one of the most widely used metal tube bending methods, the rotary draw bending (RDB) process enables reliable and high-precision metal tube bending forming (MTBF). The forming accuracy is seriously affected by the springback and other potential forming defects, of which the mechanism analysis is difficult to deal with. At the same time, the existing methods are mainly conducted in offline space, ignoring the real-time information in the physical world, which is unreliable and inefficient. To address this issue, a digital-twin-enhanced (DT-enhanced) metal tube bending forming real-time prediction method based on multi-source-input multi-task learning (MTL) is proposed. The new method can achieve comprehensive MTBF real-time prediction. By sharing the common feature of the multi-close domain and adopting group regularization strategy on feature sharing and accepting layers, the accuracy and efficiency of the multi-source-input MTL can be guaranteed. Enhanced by DT, the physical real-time deformation data is aligned in the image dimension by an improved Grammy Angle Field (GAF) conversion, realizing the reflection of the actual processing. Different from the traditional offline prediction methods, the new method integrates the virtual and physical data to achieve a more efficient and accurate real-time prediction result. and the DT mapping connection between virtual and physical systems can be achieved. To exclude the effects of equipment errors, the effectiveness of the proposed method is verified on the physical experiment-verified FE simulation scenarios. At the same time, the common pre-training networks are compared with the proposed method. The results show that the proposed DT-enhanced prediction method is more accurate and efficient.
Although existing machine reading comprehension models are making rapid progress on many datasets, they are far from robust. In this paper, we propose an understanding-oriented machine reading comprehension model to address three kinds of robustness issues, which are over sensitivity, over stability and generalization. Specifically, we first use a natural language inference module to help the model understand the accurate semantic meanings of input questions so as to address the issues of over sensitivity and over stability. Then in the machine reading comprehension module, we propose a memory-guided multi-head attention method that can further well understand the semantic meanings of input questions and passages. Third, we propose a multilanguage learning mechanism to address the issue of generalization. Finally, these modules are integrated with a multi-task learning based method. We evaluate our model on three benchmark datasets that are designed to measure models robustness, including DuReader (robust) and two SQuAD-related datasets. Extensive experiments show that our model can well address the mentioned three kinds of robustness issues. And it achieves much better results than the compared state-of-the-art models on all these datasets under different evaluation metrics, even under some extreme and unfair evaluations. The source code of our work is available at: https://github.com/neukg/RobustMRC.
Reliable quantitative analysis of immunohistochemical staining images requires accurate and robust cell detection and classification. Recent weakly-supervised methods usually estimate probability density maps for cell recognition. However, in dense cell scenarios, their performance can be limited by pre- and post-processing as it is impossible to find a universal parameter setting. In this paper, we introduce an end-to-end framework that applies direct regression and classification for preset anchor points. Specifically, we propose a pyramidal feature aggregation strategy to combine low-level features and high-level semantics simultaneously, which provides accurate cell recognition for our purely point-based model. In addition, an optimized cost function is designed to adapt our multi-task learning framework by matching ground truth and predicted points. The experimental results demonstrate the superior accuracy and efficiency of the proposed method, which reveals the high potentiality in assisting pathologist assessments.
Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization by transforming existing, supervised datasets into a diversity of novel pretraining tasks, highlighting the benefits of meta-dataset curation. While successful in general-domain text, translating these data-centric approaches to biomedical language modeling remains challenging, as labeled biomedical datasets are significantly underrepresented in popular data hubs. To address this challenge, we introduce BigBIO a community library of 126+ biomedical NLP datasets, currently covering 12 task categories and 10+ languages. BigBIO facilitates reproducible meta-dataset curation via programmatic access to datasets and their metadata, and is compatible with current platforms for prompt engineering and end-to-end few/zero shot language model evaluation. We discuss our process for task schema harmonization, data auditing, contribution guidelines, and outline two illustrative use cases: zero-shot evaluation of biomedical prompts and large-scale, multi-task learning. BigBIO is an ongoing community effort and is available at https://github.com/bigscience-workshop/biomedical
Automatic segmentation of the placenta in fetal ultrasound (US) is challenging due to the (i) high diversity of placenta appearance, (ii) the restricted quality in US resulting in highly variable reference annotations, and (iii) the limited field-of-view of US prohibiting whole placenta assessment at late gestation. In this work, we address these three challenges with a multi-task learning approach that combines the classification of placental location (e.g., anterior, posterior) and semantic placenta segmentation in a single convolutional neural network. Through the classification task the model can learn from larger and more diverse datasets while improving the accuracy of the segmentation task in particular in limited training set conditions. With this approach we investigate the variability in annotations from multiple raters and show that our automatic segmentations (Dice of 0.86 for anterior and 0.83 for posterior placentas) achieve human-level performance as compared to intra- and inter-observer variability. Lastly, our approach can deliver whole placenta segmentation using a multi-view US acquisition pipeline consisting of three stages: multi-probe image acquisition, image fusion and image segmentation. This results in high quality segmentation of larger structures such as the placenta in US with reduced image artifacts which are beyond the field-of-view of single probes.
Keyword spotting (KWS) plays an essential role in enabling speech-based user interaction on smart devices, and conventional KWS (C-KWS) approaches have concentrated on detecting user-agnostic pre-defined keywords. However, in practice, most user interactions come from target users enrolled in the device which motivates to construct personalized keyword spotting. We design two personalized KWS tasks; (1) Target user Biased KWS (TB-KWS) and (2) Target user Only KWS (TO-KWS). To solve the tasks, we propose personalized keyword spotting through multi-task learning (PK-MTL) that consists of multi-task learning and task-adaptation. First, we introduce applying multi-task learning on keyword spotting and speaker verification to leverage user information to the keyword spotting system. Next, we design task-specific scoring functions to adapt to the personalized KWS tasks thoroughly. We evaluate our framework on conventional and personalized scenarios, and the results show that PK-MTL can dramatically reduce the false alarm rate, especially in various practical scenarios.
We present Burst2Vec, our multi-task learning approach to predict emotion, age, and origin (i.e., native country/language) from vocal bursts. Burst2Vec utilises pre-trained speech representations to capture acoustic information from raw waveforms and incorporates the concept of model debiasing via adversarial training. Our models achieve a relative 30 % performance gain over baselines using pre-extracted features and score the highest amongst all participants in the ICML ExVo 2022 Multi-Task Challenge.
Acoustic events are sounds with well-defined spectro-temporal characteristics which can be associated with the physical objects generating them. Acoustic scenes are collections of such acoustic events in no specific temporal order. Given this natural linkage between events and scenes, a common belief is that the ability to classify events must help in the classification of scenes. This has led to several efforts attempting to do well on Acoustic Event Tagging (AET) and Acoustic Scene Classification (ASC) using a multi-task network. However, in these efforts, improvement in one task does not guarantee an improvement in the other, suggesting a tension between ASC and AET. It is unclear if improvements in AET translates to improvements in ASC. We explore this conundrum through an extensive empirical study and show that under certain conditions, using AET as an auxiliary task in the multi-task network consistently improves ASC performance. Additionally, ASC performance further improves with the AET data-set size and is not sensitive to the choice of events or the number of events in the AET data-set. We conclude that this improvement in ASC performance comes from the regularization effect of using AET and not from the network's improved ability to discern between acoustic events.