skip to main content

Title: Deep Multi-Task Learning with Adversarial-and-Cooperative Nets
In this paper, we propose a deep multi-Task learning model based on Adversarial-and-COoperative nets (TACO). The goal is to use an adversarial-and-cooperative strategy to decouple the task-common and task-specific knowledge, facilitating the fine-grained knowledge sharing among tasks. TACO accommodates multiple game players, i.e., feature extractors, domain discriminator, and tri-classifiers. They play the MinMax games adversarially and cooperatively to distill the task-common and task-specific features, while respecting their discriminative structures. Moreover, it adopts a divide-and-combine strategy to leverage the decoupled multi-view information to further improve the generalization performance of the model. The experimental results show that our proposed method significantly outperforms the state-of-the-art algorithms on the benchmark datasets in both multi-task learning and semi-supervised domain adaptation scenarios.
; ; ; ;
Award ID(s):
1947135 1651203
Publication Date:
Journal Name:
Page Range or eLocation-ID:
4078 to 4084
Sponsoring Org:
National Science Foundation
More Like this
  1. In this paper, we propose Task-Adversarial co-Generative Nets (TAGN) for learning from multiple tasks. It aims to address the two fundamental issues of multi-task learning, i.e., domain shift and limited labeled data, in a principled way. To this end, TAGN first learns the task-invariant representations of features to bridge the domain shift among tasks. Based on the task-invariant features, TAGN generates the plausible examples for each task to tackle the data scarcity issue. In TAGN, we leverage multiple game players to gradually improve the quality of the co-generation of features and examples by using an adversarial strategy. It simultaneously learns the marginal distribution of task-invariant features across different tasks and the joint distributions of examples with labels for each task. The theoretical study shows the desired results: at the equilibrium point of the multi-player game, the feature extractor exactly produces the task-invariant features for different tasks, while both the generator and the classifier perfectly replicate the joint distribution for each task. The experimental results on the benchmark data sets demonstrate the effectiveness of the proposed approach.
  2. This paper proposes an evolutionary transfer learning approach (Evol-TL) for scalable quality-of-transmission (QoT) estimation in multi-domain elastic optical networks (MD-EONs). Evol-TL exploits a broker-based MD-EON architecture that enables cooperative learning between the broker plane (end-to-end) and domain-level (local) machine learning functions while securing the autonomy of each domain. We designed a genetic algorithm to optimize the neural network architectures and the sets of weights to be transferred between the source and destination tasks. We evaluated the performance of Evol-TL with three case studies considering the QoT estimation task for lightpaths with (i) different path lengths (in terms of the numbers of fiber links traversed), (ii) different modulation formats, and (iii) different device conditions (emulated by introducing different levels of wavelength-specific attenuation to the amplifiers). The results show that the proposed approach can reduce the average amount of required training data by up to13×<#comment/>while achieving an estimation accuracy above 95%.

  3. During disasters, it is critical to deliver emergency information to appropriate first responders. Name-based information delivery provides efficient, timely dissemination of relevant content to first responder teams assigned to different incident response roles. People increasingly depend on social media for communicating vital information, using free-form text. Thus, a method that delivers these social media posts to the right first responders can significantly improve outcomes. In this paper, we propose FLARE, a framework using 'Social Media Engines' (SMEs) to map social media posts (SMPs), such as tweets, to the right names. SMEs perform natural language processing-based classification and exploit several machine learning capabilities, in an online real-time manner. To reduce the manual labeling effort required for learning during the disaster, we leverage active learning, complemented by dispatchers with specific domain-knowledge performing limited labeling. We also leverage federated learning across various public-safety departments with specialized knowledge to handle notifications related to their roles in a cooperative manner. We implement three different classifiers: for incident relevance, organization, and fine-grained role prediction. Each class is associated with a specific subset of the namespace graph. The novelty of our system is the integration of the namespace with federated active learning and inference procedures to identifymore »and deliver vital SMPs to the right first responders in a distributed multi-organization environment, in real-time. Our experiments using real-world data, including tweets generated by citizens during the wildfires in California in 2018, show our approach outperforming both a simple keyword-based classification and several existing NLP-based classification techniques.« less
  4. Domain adaptation is critical for success in new, unseen environments. Adversarial adaptation models have shown tremendous progress towards adapting to new environments by focusing either on discovering domain invariant representations or by mapping between unpaired image domains. While feature space methods are difficult to interpret and sometimes fail to capture pixel-level and low-level domain shifts, image space methods sometimes fail to incorporate high level semantic knowledge relevant for the end task. We propose a model which adapts between domains using both generative image space alignment and latent representation space alignment. Our approach, Cycle-Consistent Adversarial Domain Adaptation (CyCADA), guides transfer between domains according to a specific discriminatively trained task and avoids divergence by enforcing consistency of the relevant semantics before and after adaptation. We evaluate our method on a variety of visual recognition and prediction settings, including digit classification and semantic segmentation of road scenes, advancing state-of-the-art performance for unsupervised adaptation from synthetic to real world driving domains.
  5. Abstract Motivation Detecting cancer gene expression and transcriptome changes with mRNA-sequencing (RNA-Seq) or array-based data are important for understanding the molecular mechanisms underlying carcinogenesis and cellular events during cancer progression. In previous studies, the differentially expressed genes were detected across patients in one cancer type. These studies ignored the role of mRNA expression changes in driving tumorigenic mechanisms that are either universal or specific in different tumor types. To address the problem, we introduce two network-based multi-task learning frameworks, NetML and NetSML, to discover common differentially expressed genes shared across different cancer types as well as differentially expressed genes specific to each cancer type. The proposed frameworks consider the common latent gene co-expression modules and gene-sample biclusters underlying the multiple cancer datasets to learn the knowledge crossing different tumor types. Results Large-scale experiments on simulations and real cancer high-throughput datasets validate that the proposed network-based multi-task learning frameworks perform better sample classification compared with the models without the knowledge sharing across different cancer types. The common and cancer specific molecular signatures detected by multi-task learning frameworks on TCGA ovarian cancer, breast cancer, and prostate cancer datasets are correlated with the known marker genes and enriched in cancer relevant KEGG pathwaysmore »and Gene Ontology terms. Availability and Implementation Source code is available at: Supplementary information Supplementary data are available at Bioinformatics« less