Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding

Knowledge Graph (KG) alignment is to discover the mappings (i.e., equivalent entities, relations, and others) between two KGs. The existing methods can be divided into the embedding-based models, and the conventional reasoning and lexical matching based systems. The former compute the similarity of entities via their cross-KG embeddings, but they usually rely on an ideal supervised learning setting for good performance and lack appropriate reasoning to avoid logically wrong mappings; while the latter address the reasoning issue but are poor at utilizing the KG graph structures and the entity contexts. In this study, we aim at combining the above two solutions and thus propose an iterative framework named PRASE which is based on probabilistic reasoning and semantic embedding. It learns the KG embeddings via entity mappings from a probabilistic reasoning system named PARIS, and feeds the resultant entity mappings and embeddings back into PARIS for augmentation. The PRASE framework is compatible with different embedding-based models, and our experiments on multiple datasets have demonstrated its state-of-the-art performance.

New Multi-View Classification Method with Uncertain Data

Multi-view classification aims at designing a multi-view learning strategy to train a classifier from multi-view data, which are easily collected in practice. Most of the existing works focus on multi-view classification by assuming the multi-view data are collected with precise information. However, we always collect the uncertain multi-view data due to the collection process is corrupted with noise in real-life application. In this case, this article proposes a novel approach, called uncertain multi-view learning with support vector machine (UMV-SVM) to cope with the problem of multi-view learning with uncertain data. The method first enforces the agreement among all the views to seek complementary information of multi-view data and takes the uncertainty of the multi-view data into consideration by modeling reachability area of the noise. Then it proposes an iterative framework to solve the proposed UMV-SVM model such that we can obtain the multi-view classifier for prediction. Extensive experiments on real-life datasets have shown that the proposed UMV-SVM can achieve a better performance for uncertain multi-view classification in comparison to the state-of-the-art multi-view classification methods.

Framwork for fieldwork and documentation in primary Research

This paper presents an iterative framework for carrying out fieldworks on biodeterioration studies in the built environment with specific reference to the fieldwork on Microbial Colonisation of Building Finishes and Facings in Enugu. The paper discusses the step-by-step preparations prior to and during fieldwork and their importance in fruitful data collection, respondent’s responses and accompanied field interview. It highlights the pros and cons of fieldwork showing reasons why fieldwork is vital in biodeterioration research in the built environment. In doing so, the various stages of the fieldwork are discussed with their implications. At the end of the fieldwork, useful lessons learnt include the essence of digital compass in geolocation, the effect of good first impression during interview, and sourcing of data from government and organizations amongst others.

An Iterative Scheme of Safe Reinforcement Learning for Nonlinear Systems via Barrier Certificate Generation

In this paper, we propose a safe reinforcement learning approach to synthesize deep neural network (DNN) controllers for nonlinear systems subject to safety constraints. The proposed approach employs an iterative scheme where a learner and a verifier interact to synthesize safe DNN controllers. The learner trains a DNN controller via deep reinforcement learning, and the verifier certifies the learned controller through computing a maximal safe initial region and its corresponding barrier certificate, based on polynomial abstraction and bilinear matrix inequalities solving. Compared with the existing verification-in-the-loop synthesis methods, our iterative framework is a sequential synthesis scheme of controllers and barrier certificates, which can learn safe controllers with adaptive barrier certificates rather than user-defined ones. We implement the tool SRLBC and evaluate its performance over a set of benchmark examples. The experimental results demonstrate that our approach efficiently synthesizes safe DNN controllers even for a nonlinear system with dimension up to 12.

Keep it Unsupervised: Horizontal Attacks Meet Deep Learning

To mitigate side-channel attacks, real-world implementations of public-key cryptosystems adopt state-of-the-art countermeasures based on randomization of the private or ephemeral keys. Usually, for each private key operation, a “scalar blinding” is performed using 32 or 64 randomly generated bits. Nevertheless, horizontal attacks based on a single trace still pose serious threats to protected ECC or RSA implementations. If the secrets learned through a single-trace attack contain too many wrong (or noisy) bits, the cryptanalysis methods for recovering remaining bits become impractical due to time and computational constraints. This paper proposes a deep learning-based framework to iteratively correct partially correct private keys resulting from a clustering-based horizontal attack. By testing the trained network on scalar multiplication (or exponentiation) traces, we demonstrate that a deep neural network can significantly reduce the number of wrong bits from randomized scalars (or exponents).When a simple horizontal attack can recover around 52% of attacked multiple private key bits, the proposed iterative framework improves the private key accuracy to above 90% on average and to 100% for at least one of the attacked keys. Our attack model remains fully unsupervised and excludes the need to know where the error or noisy bits are located in each separate randomized private key.

Iterative Framework and Privacy Preservation in Reciprocal Recommendation.

: Although there are many reciprocal recommenders based on different strategies which have found applications in different domains but in this paper we aim to design a common framework for both symmetric as well as asymmetric reciprocal recommendation systems (in Indian context), namely Job recommendation (asymmetric) and Online Indian matrimonial system (symmetric).The contributions of this paper is multifold: i) Iterative framework for Reciprocal Recommendation for symmetric as well as asymmetric systems. ii) Useful information extracted from explicit as well as implicit sources which were not explored in the existing system (Free-text mining in Indian Matchmaking System). iii) Considered job-seekers’ personal information like his marital status, kids, current location for suggesting recommendation. These parameters are very important from practical viewpoint of a user, how he perceives a job opening. iv) Proposed Privacy preservation in the proposed framework for Reciprocal Recommendation system. We have achieved improved efficiency through our framework as compared to the existing system.