Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol

Hedegaard, Lukas; Sheikh-Omar, Omar Ali; Iosifidis, Alexandros

doi:10.1109/tip.2021.3118978

Cited by 20 publications

(19 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In (Long et al, 2015), a Deep Adaptation Network (DAN) architecture was proposed that uses maximum mean discrepancy (MMD) (Gretton et al, 2012) to find a domain-invariant feature space. In (Hedegaard et al, 2021), it was shown that supervised DA can be seen as a two-view Graph Embedding. In (Pratama et al, 2019b), a method was proposed that combines DA techniques and drift handling mechanism to solve the multistream classification problem under multisource streams.…”

Section: Model Re-usabilitymentioning

confidence: 99%

“…There have been different approaches to reduce computational complexity when training deep neural networks, such as designing novel low-complexity network architectures (Kiranyaz et al, 2017;Tran et al, 2019c;Tran & Iosifidis, 2019;Tran et al, 2020;Kiranyaz et al, 2020;Heidari & Iosifidis, 2020), replacing existing ones with their low-rank counterparts (Denton et al, 2014;Jaderberg et al, 2014;Tran et al, 2018;Huang & Yu, 2018;Ruan et al, 2020), or adapting the pre-trained models to new tasks, i.e., performing Transfer Learning (TL) (Shao et al, 2014;Yang et al, 2015;Ding et al, 2016;Ding & Fu, 2018;Fons et al, 2020) or Domain Adaptation (DA) learning (Duan et al, 2012;Wang et al, 2019;Zhao et al, 2020;Hedegaard et al, 2021). Among these approaches, model adaptation is the most versatile since a method in this category is often architecture-agnostic, being complementary to other approaches.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classification

Shabani¹,

Tran²,

Kanniainen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Deep Learning models have become dominant in tackling financial time-series analysis problems, overturning conventional machine learning and statistical methods. Most often, a model trained for one market or security cannot be directly applied to another market or security due to differences inherent in the market conditions. In addition, as the market evolves through time, it is necessary to update the existing models or train new ones when new data is made available. This scenario, which is inherent in most financial forecasting applications, naturally raises the following research question: How to efficiently adapt a pre-trained model to a new set of data while retaining performance on the old data, especially when the old data is not accessible? In this paper, we propose a method to efficiently retain the knowledge available in a neural network pretrained on a set of securities and adapt it to achieve high performance in new ones. In our method, the prior knowledge encoded in a pre-trained neural network is maintained by keeping existing connections fixed, and this knowledge is adjusted for the new securities by a set of augmented connections, which are optimized using the new data. The auxiliary connections are constrained to be of low rank. This not only allows us to rapidly optimize for the new task but also reduces the storage and run-time complexity during the deployment phase. The efficiency of our approach is empirically validated in the stock midprice movement prediction problem using a large-scale limit order book dataset. Experimental results show that our approach enhances prediction performance as well as reduces the overall number of network parameters.

show abstract

Section: Model Re-usabilitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classification

Shabani¹,

Tran²,

Kanniainen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Next, a few labeled target observations are used as reference points to adjust similarity structures among label categories. Finally, we refer to the work by Hedegaard et al [47] for a discussion and critic of the generic test setup used in the supervised domain adaptation literature and a proposal of a fair evaluation protocol.…”

Section: Neural Network Deep Learning and Transfer Learningmentioning

confidence: 99%

Fighting Money Laundering with Statistics and Machine Learning

Jensen¹,

Iosifidis²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Money laundering is a profound, global problem. Nonetheless, there is little statistical and machine learning research on the topic. In this paper, we focus on anti-money laundering in banks. To help organize existing research in the field, we propose a unifying terminology and provide a review of the literature. This is structured around two central tasks: (i) client risk profiling and (ii) suspicious behavior flagging. We find that client risk profiling is characterized by diagnostics, i.e., efforts to find and explain risk factors. Suspicious behavior flagging, on the other hand, is characterized by non-disclosed features and hand-crafted risk indices. Finally, we discuss directions for future research. One major challenge is the lack of public data sets. This may, potentially, be addressed by synthetic data generation. Other possible research directions include semi-supervised and deep learning, interpretability and fairness of the results.

show abstract

“…In a semi-supervised DA (SSDA) scheme [ 8 ], both a small amount of labeled and a considerable amount of unlabelled data are accessible. Alternatively, supervised domain adaptation (SDA) [ 9 , 10 ] supposes that all available target samples are annotated, although the number is small. Sophisticated SDA approaches can usually outperform UDA and SSDA ones when the amount of available data in is small [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

Center transfer for supervised domain adaptation

et al. 2023

View full text Add to dashboard Cite

Domain adaptation (DA) is a popular strategy for pattern recognition and classification tasks. It leverages a large amount of data from the source domain to help train the model applied in the target domain. Supervised domain adaptation (SDA) approaches are desirable when only few labeled samples from the target domain are available. They can be easily adopted in many real-world applications where data collection is expensive. In this study, we propose a new supervision signal, namely center transfer loss (CTL), to efficiently align features under the SDA setting in the deep learning (DL) field. Unlike most previous SDA methods that rely on pairing up training samples, the proposed loss is trainable only using one-stream input based on the mini-batch strategy. The CTL exhibits two main functionalities in training to increase the performance of DL models, i.e., domain alignment and increasing the feature’s discriminative power. The hyper-parameter to balance these two functionalities is waived in CTL, which is the second improvement from the previous approaches. Extensive experiments completed on well-known public datasets show that the proposed method performs better than recent state-of-the-art approaches.

show abstract

Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol

Cited by 20 publications

References 40 publications

Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classification

Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classification

Fighting Money Laundering with Statistics and Machine Learning

Center transfer for supervised domain adaptation

Contact Info

Product

Resources

About