Search

Domain adaptation is becoming increasingly important for learning systems in recent years, especially with the growing diversification of data domains in real-world applications, such as the genetic data from various sequencing platforms and video feeds from multiple surveillance cameras. Traditional domain adaptation approaches target to design transformations for each individual domain so that the twisted data from different domains follow an almost identical distribution. In many applications, however, the data from diversified domains are simply dumped to an archive even without clear domain labels. In this article, we discuss the possibility of learning domain adaptations even when the data does not contain domain labels. Our solution is based on our new model, named domain adaption using cross-domain homomorphism (DACH in short), to identify intrinsic homomorphism hidden in mixed data from all domains. DACH is generally compatible with existing deep learning frameworks, enabling the generation of nonlinear features from the original data domains. Our theoretical analysis not only shows the universality of the homomorphism, but also proves the convergence of DACH for significant homomorphism structures over the data domains is preserved. Empirical studies on real-world data sets validate the effectiveness of DACH on merging multiple data domains for joint machine learning tasks and the scalability of our algorithm to domain dimensionality. [ABSTRACT FROM AUTHOR]

Scalable causal discovery is an essential technology to a wide spectrum of applications, including biomedical studies and social network evolution analysis. To tackle the difficulty of high dimensionality, a number of solutions are proposed in the literature, generally dividing the original variable domain into smaller subdomains by computation intensive partitioning strategies. These approaches usually suffer significant structural errors when the partitioning strategies fail to recognize true causal edges across the output subdomains. Such a structural error accumulates quickly with the growing depth of recursive partitioning, due to the lack of correction mechanism over causally connected variables when they are wrongly divided into two subdomains, finally jeopardizing the robustness of the integrated results. This paper proposes a completely different strategy to solve the problem, powered by a lightweight random partitioning scheme together with a carefully designed merging algorithm over results from the random partitions. Based on the randomness properties of the partitioning scheme, we design a suite of tricks for the merging algorithm, in order to support propagation-based significance enhancement, maximal acyclic subgraph causal ordering, and order-sensitive redundancy elimination. Theoretical studies as well as empirical evaluations verify the genericity, effectiveness, and scalability of our proposal on both simulated and real-world causal structures when the scheme is used in combination with a variety of causal solvers known effective on smaller domains. [ABSTRACT FROM AUTHOR]

Social causality study on human action sequences is useful and important to improve our understandings to human behaviors on online social networks. The redundant indirect causalities and unobserved confounding factors, such as homophily and simultaneity phenomena, contribute to the huge challenges on accurate causal discovery on such human actions. A causal relationship exists between two persons, if the actions of one person are significantly affected by the actions of the other person, while fairly independent of her/his own prior actions. In this paper, we design a systematic approach based on conditional independence testing to detect such asymmetric relations, even when there are latent confounders underneath the observational action sequences. Technically, a group of asymmetric independence tests are conducted to infer the loose causal directions between action sequence pairs, followed by another group of tests to distinguish different types of relationships, e.g., homophily and simultaneity. Finally, a causal structure learning method is employed to output pairwise causalities with redundant indirect causalities eliminated. Empirical evaluations on simulated data verify the effectiveness and scalability of our proposals. We also present four interesting patterns of causal relations found by our algorithm, on real Sina Weibo feeds, including two new patterns never reported in previous studies. [ABSTRACT FROM AUTHOR]