In this letter, we introduce over-the-air computation into the communication design of federated multi-task learning (FMTL), and propose an over-the-air federated multi-task learning (OA-FMTL) framework, where multiple learning tasks deployed on edge devices share a non-orthogonal fading channel under the coordination of an edge server (ES). Specifically, the model updates for all the tasks are transmitted and superimposed concurrently over a non-orthogonal uplink fading channel, and the model aggregations of all the tasks are reconstructed at the ES through a modified version of the turbo compressed sensing algorithm (Turbo-CS) that overcomes inter-task interference. Both convergence analysis and numerical results show that the OA-FMTL framework can significantly improve the system efficiency in terms of reducing the number of channel uses without causing substantial learning performance degradation.
Low-prior targets are common among many important clinical events, which introduces the challenge of having enough data to support learning of their predictive models. Many prior works have addressed this problem by first building a general patient-state representation model, and then adapting it to a new low-prior prediction target. In this schema, there is potential for the predictive performance to be hindered by the misalignment between the general patient-state model and the target task. To overcome this challenge, we propose a new method that simultaneously optimizes a shared model through multi-task learning of both the low-prior supervised target and general purpose patient-state representation (GPSR). More specifically, our method improves prediction performance of a low-prior task by jointly optimizing a shared model that combines the loss of the target event and a broad range of generic clinical events. We study the approach in the context of Recurrent Neural Networks (RNNs). Through extensive experiments on multiple clinical event targets using MIMIC-III data, we show that the inclusion of general patient-state representation tasks during model training improves the prediction of individual low-prior targets.
This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV). In the proposed structure, the frame-level multi-task learning along with the segment-level adversarial learning is adopted for speaker embedding extraction. The phoneme-aware attentive pooling is exploited on frame-level features in the main network for speaker classifier, with the corresponding posterior probability for the phoneme distribution in the auxiliary subnet. Further, the introduction of Squeeze and Excitation (SE-block) performs dynamic channel-wise feature recalibration, which improves the representational ability. The proposed method exploits speaker idiosyncrasies associated with pass-phrases, and is further improved by the phoneme-aware attentive pooling and SE-block from temporal and channel-wise aspects, respectively. The experiments conducted on RSR2015 Part 1 database confirm that the proposed system achieves outstanding results for textdependent SV.
Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider a novel problem of learning a shared generative model that is useful across various visual perception tasks. Correspondingly, we propose a general multi-task oriented generative modeling (MGM) framework, by coupling a discriminative multi-task network with a generative network. While it is challenging to synthesize both RGB images and pixel-level annotations in multi-task scenarios, our framework enables us to use synthesized images paired with only weak annotations (i.e., image-level scene labels) to facilitate multiple visual tasks. Experimental evaluation on challenging multi-task benchmarks, including NYUv2 and Taskonomy, demonstrates that our MGM framework improves the performance of all the tasks by large margins, consistently outperforming state-of-the-art multi-task approaches.
In recent years, there have been significant developments in Question Answering over Knowledge Graphs (KGQA). Despite all the notable advancements, current KGQA systems only focus on answer generation techniques and not on answer verbalization. However, in real-world scenarios (e.g., voice assistants such as Alexa, Siri, etc.), users prefer verbalized answers instead of a generated response. This paper addresses the task of answer verbalization for (complex) question answering over knowledge graphs. In this context, we propose a multi-task-based answer verbalization framework: VOGUE (Verbalization thrOuGh mUlti-task lEarning). The VOGUE framework attempts to generate a verbalized answer using a hybrid approach through a multi-task learning paradigm. Our framework can generate results based on using questions and queries as inputs concurrently. VOGUE comprises four modules that are trained simultaneously through multi-task learning. We evaluate our framework on existing datasets for answer verbalization, and it outperforms all current baselines on both BLEU and METEOR scores.
Dialect and standard language identification are crucial tasks for many Arabic natural language processing applications. In this paper, we present our deep learning-based system, submitted to the second NADI shared task for country-level and province-level identification of Modern Standard Arabic (MSA) and Dialectal Arabic (DA). The system is based on an end-to-end deep Multi-Task Learning (MTL) model to tackle both country-level and province-level MSA/DA identification. The latter MTL model consists of a shared Bidirectional Encoder Representation Transformers (BERT) encoder, two task-specific attention layers, and two classifiers. Our key idea is to leverage both the task-discriminative and the inter-task shared features for country and province MSA/DA identification. The obtained results show that our MTL model outperforms single-task models on most subtasks.
The prominence of figurative language devices, such as sarcasm and irony, poses serious challenges for Arabic Sentiment Analysis (SA). While previous research works tackle SA and sarcasm detection separately, this paper introduces an end-to-end deep Multi-Task Learning (MTL) model, allowing knowledge interaction between the two tasks. Our MTL model's architecture consists of a Bidirectional Encoder Representation from Transformers (BERT) model, a multi-task attention interaction module, and two task classifiers. The overall obtained results show that our proposed model outperforms its single-task counterparts on both SA and sarcasm detection sub-tasks.
Moving objects have special importance for Autonomous Driving tasks. Detecting moving objects can be posed as Moving Object Segmentation, by segmenting the object pixels, or Moving Object Detection, by generating a bounding box for the moving targets. In this paper, we present a Multi-Task Learning architecture, based on Transformers, to jointly perform both tasks through one network. Due to the importance of the motion features to the task, the whole setup is based on a Spatio-Temporal aggregation. We evaluate the performance of the individual tasks architecture versus the MTL setup, both with early shared encoders, and late shared encoder-decoder transformers. For the latter, we present a novel joint tasks query decoder transformer, that enables us to have tasks dedicated heads out of the shared model. To evaluate our approach, we use the KITTI MOD [29] data set. Results show1.5% mAP improvement for Moving Object Detection, and 2%IoU improvement for Moving Object Segmentation, over the individual tasks networks.
Predicting multiple heterogeneous biological and medical targets is a challenge for traditional deep learning models. In contrast to single-task learning, in which a separate model is trained for each target, multi-task learning (MTL) optimizes a single model to predict multiple related targets simultaneously. To address this challenge, we propose the Multi-gate Mixture-of-Experts with Exclusivity (MMoEEx). Our work aims to tackle the heterogeneous MTL setting, in which the same model optimizes multiple tasks with different characteristics. Such a scenario can overwhelm current MTL approaches due to the challenges in balancing shared and task-specific representations and the need to optimize tasks with competing optimization paths. Our method makes two key contributions: first, we introduce an approach to induce more diversity among experts, thus creating representations more suitable for highly imbalanced and heterogenous MTL learning; second, we adopt a two-step optimization [6, 11] approach to balancing the tasks at the gradient level. We validate our method on three MTL benchmark datasets, including Medical Information Mart for Intensive Care (MIMIC-III) and PubChem BioAssay (PCBA).
Question generation (QG) is to generate natural and grammatical questions that can be answered by a specific answer for a given context. Previous sequence-to-sequence models suffer from a problem that asking high-quality questions requires commonsense knowledge as backgrounds, which in most cases can not be learned directly from training data, resulting in unsatisfactory questions deprived of knowledge. In this paper, we propose a multi-task learning framework to introduce commonsense knowledge into question generation process. We first retrieve relevant commonsense knowledge triples from mature databases and select triples with the conversion information from source context to question. Based on these informative knowledge triples, we design two auxiliary tasks to incorporate commonsense knowledge into the main QG model, where one task is Concept Relation Classification and the other is Tail Concept Generation. Experimental results on SQuAD show that our proposed methods are able to noticeably improve the QG performance on both automatic and human evaluation metrics, demonstrating that incorporating external commonsense knowledge with multi-task learning can help the model generate human-like and high-quality questions.
Transferability estimation is an essential problem in transfer learning to predict how good the performance is when transferring a source model (or source task) to a target task. Recent analytical transferability metrics have been widely used for source model selection and multi-task learning. A major challenge is how to make transfereability estimation robust under the cross-domain cross-task settings. The recently proposed OTCE score solves this problem by considering both domain and task differences, with the help of transfer experiences on auxiliary tasks, which causes an efficiency overhead. In this work, we propose a practical transferability metric called JC-NCE score that dramatically improves the robustness of the task difference estimation in OTCE, thus removing the need for auxiliary tasks. Specifically, we build the joint correspondences between source and target data via solving an optimal transport problem with a ground cost considering both the sample distance and label distance, and then compute the transferability score as the negative conditional entropy of the matched labels. Extensive validations under the intra-dataset and inter-dataset transfer settings demonstrate that our JC-NCE score outperforms the auxiliary-task free version of OTCE for 7% and 12%, respectively, and is also more robust than other existing transferability metrics on average.
Nowadays, live video streaming events have become a mainstay in viewer's communication in large international enterprises. Provided that viewers are distributed worldwide, the main challenge resides on how to schedule the optimal event's time so as to improve both the viewer's engagement and adoption. In this paper we present a multi-task deep reinforcement learning model to select the time of a live video streaming event, aiming to optimize the viewer's engagement and adoption at the same time. We consider the engagement and adoption of the viewers as independent tasks and formulate a unified loss function to learn a common policy. In addition, we account for the fact that each task might have different contribution to the training strategy of the agent. Therefore, to determine the contribution of each task to the agent's training, we design a Transformer's architecture for the state-action transitions of each task. We evaluate our proposed model on four real-world datasets, generated by the live video streaming events of four large enterprises spanning from January 2019 until March 2021. Our experiments demonstrate the effectiveness of the proposed model when compared with several state-of-the-art strategies. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://github.com/stefanosantaris/merlin.
Multi-task learning (MTL) has been successfully applied to many recommendation applications. However, MTL models often suffer from performance degeneration with negative transfer due to the complex and competing task correlation in real-world recommender systems. Moreover, through extensive experiments across SOTA MTL models, we have observed an interesting seesaw phenomenon that performance of one task is often improved by hurting the performance of some other tasks. To address these issues, we propose a Progressive Layered Extraction (PLE) model with a novel sharing structure design. PLE separates shared components and task-specific components explicitly and adopts a progressive routing mechanism to extract and separate deeper semantic knowledge gradually, improving efficiency of joint representation learning and information routing across tasks in a general setup. We apply PLE to both complicatedly correlated and normally correlated tasks, ranging from two-task cases to multi-task cases on a real-world Tencent video recommendation dataset with 1 billion samples, and results show that PLE outperforms state-of-the-art MTL models significantly under different task correlations and task-group size. Furthermore, online evaluation of PLE on a large-scale content recommendation platform at Tencent manifests 2.23% increase in view-count and 1.84% increase in watch time compared to SOTA MTL models, which is a significant improvement and demonstrates the effectiveness of PLE. Finally, extensive offline experiments on public benchmark datasets demonstrate that PLE can be applied to a variety of scenarios besides recommendations to eliminate the seesaw phenomenon. PLE now has been deployed to the online video recommender system in Tencent successfully.
Dysarthric speech detection (DSD) systems aim to detect characteristics of the neuromotor disorder from speech. Such systems are particularly susceptible to domain mismatch where the training and testing data come from the source and target domains respectively, but the two domains may differ in terms of speech stimuli, disease etiology, etc. It is hard to acquire labelled data in the target domain, due to high costs of annotating sizeable datasets. This paper makes a first attempt to formulate cross-domain DSD as an unsupervised domain adaptation (UDA) problem. We use labelled source-domain data and unlabelled target-domain data, and propose a multi-task learning strategy, including dysarthria presence classification (DPC), domain adversarial training (DAT) and mutual information minimization (MIM), which aim to learn dysarthria-discriminative and domain-invariant biomarker embeddings. Specifically, DPC helps biomarker embeddings capture critical indicators of dysarthria; DAT forces biomarker embeddings to be indistinguishable in source and target domains; and MIM further reduces the correlation between biomarker embeddings and domain-related cues. By treating the UASPEECH and TORGO corpora respectively as the source and target domains, experiments show that the incorporation of UDA attains absolute increases of 22.2% and 20.0% respectively in utterance-level weighted average recall and speaker-level accuracy.
Detecting what emotions are expressed in text is a well-studied problem in natural language processing. However, research on finer grained emotion analysis such as what causes an emotion is still in its infancy. We present solutions that tackle both emotion recognition and emotion cause detection in a joint fashion. Considering that common-sense knowledge plays an important role in understanding implicitly expressed emotions and the reasons for those emotions, we propose novel methods that combine common-sense knowledge via adapted knowledge models with multi-task learning to perform joint emotion classification and emotion cause tagging. We show performance improvement on both tasks when including common-sense reasoning and a multitask framework. We provide a thorough analysis to gain insights into model performance.
Multi-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with limited labels during the test phase, in the hope of fast adaptation over them. Despite the subtle difference between MTL and meta-learning in the problem formulation, both learning paradigms share the same insight that the shared structure between existing training tasks could lead to better generalization and adaptation. In this paper, we take one important step further to understand the close connection between these two learning paradigms, through both theoretical analysis and empirical investigation. Theoretically, we first demonstrate that MTL shares the same optimization formulation with a class of gradient-based meta-learning (GBML) algorithms. We then prove that for over-parameterized neural networks with sufficient depth, the learned predictive functions of MTL and GBML are close. In particular, this result implies that the predictions given by these two models are similar over the same unseen task. Empirically, we corroborate our theoretical findings by showing that, with proper implementation, MTL is competitive against state-of-the-art GBML algorithms on a set of few-shot image classification benchmarks. Since existing GBML algorithms often involve costly second-order bi-level optimization, our first-order MTL method is an order of magnitude faster on large-scale datasets such as mini-ImageNet. We believe this work could help bridge the gap between these two learning paradigms, and provide a computationally efficient alternative to GBML that also supports fast task adaptation.
Inter-agent communication can significantly increase performance in multi-agent tasks that require co-ordination to achieve a shared goal. Prior work has shown that it is possible to learn inter-agent communication protocols using multi-agent reinforcement learning and message-passing network architectures. However, these models use an unconstrained broadcast communication model, in which an agent communicates with all other agents at every step, even when the task does not require it. In real-world applications, where communication may be limited by system constraints like bandwidth, power and network capacity, one might need to reduce the number of messages that are sent. In this work, we explore a simple method of minimizing communication while maximizing performance in multi-task learning: simultaneously optimizing a task-specific objective and a communication penalty. We show that the objectives can be optimized using Reinforce and the Gumbel-Softmax reparameterization. We introduce two techniques to stabilize training: 50% training and message forwarding. Training with the communication penalty on only 50% of the episodes prevents our models from turning off their outgoing messages. Second, repeating messages received previously helps models retain information, and further improves performance. With these techniques, we show that we can reduce communication by 75% with no loss of performance.
In this paper, we propose a single multi-task learning framework to perform End-to-End (E2E) speech recognition (ASR) and accent recognition (AR) simultaneously. The proposed framework is not only more compact but can also yield comparable or even better results than standalone systems. Specifically, we found that the overall performance is predominantly determined by the ASR task, and the E2E-based ASR pretraining is essential to achieve improved performance, particularly for the AR task. Additionally, we conduct several analyses of the proposed method. First, though the objective loss for the AR task is much smaller compared with its counterpart of ASR task, a smaller weighting factor with the AR task in the joint objective function is necessary to yield better results for each task. Second, we found that sharing only a few layers of the encoder yields better AR results than sharing the overall encoder. Experimentally, the proposed method produces WER results close to the best standalone E2E ASR ones, while it achieves 7.7% and 4.2% relative improvement over standalone and single-task-based joint recognition methods on test set for accent recognition respectively.
Handwritten digit recognition is one of the extensively studied area in machine learning. Apart from the wider research on handwritten digit recognition on MNIST dataset, there are many other research works on various script recognition. However, it is not very common for multi-script digit recognition which encourage the development of robust and multipurpose systems. Additionally working on multi-script digit recognition enables multi-task learning, considering the script classification as a related task for instance. It is evident that multi-task learning improves model performance through inductive transfer using the information contained in related tasks. Therefore, in this study multi-script handwritten digit recognition using multi-task learning will be investigated. As a specific case of demonstrating the solution to the problem, Amharic handwritten character recognition will also be experimented. The handwritten digits of three scripts including Latin, Arabic and Kannada are studied to show that multi-task models with reformulation of the individual tasks have shown promising results. In this study a novel way of using the individual tasks predictions was proposed to help classification performance and regularize the different loss for the purpose of the main task. This finding has outperformed the baseline and the conventional multi-task learning models. More importantly, it avoided the need for weighting the different losses of the tasks, which is one of the challenges in multi-task learning.
In this paper, we propose a new data poisoning attack and apply it to deep reinforcement learning agents. Our attack centers on what we call in-distribution triggers, which are triggers native to the data distributions the model will be trained on and deployed in. We outline a simple procedure for embedding these, and other, triggers in deep reinforcement learning agents following a multi-task learning paradigm, and demonstrate in three common reinforcement learning environments. We believe that this work has important implications for the security of deep learning models.