In recent years, research interest in object retrieval has shifted from 2D towards 3D data. Despite many well-designed approaches, we point out that limitations still exist and there is tremendous room for improvement, including the heavy reliance on hand-crafted features, the separated optimization of feature extraction and object retrieval, and the lack of sufficient training samples. In this work, we address the above limitations for 3D object retrieval by developing a novel end-to-end solution named Group Pair Convolutional Neural Network (GPCNN). It can jointly learn the visual features from multiple views of a 3D model and optimize towards the object retrieval task. To tackle the insufficient training data issue, we innovatively employ a pair-wise learning scheme, which learns model parameters from the similarity of each sample pair, rather than the traditional way of learning from sparse label–sample matching. Extensive experiments on three public benchmarks show that our GPCNN solution significantly outperforms the state-of-the-art methods with 3% to 42% improvement in retrieval accuracy.

In this paper, we seek to enable machine to answer questions like, given a clutch bag, what kind of skirt, heel and even accessory best fashionably collocate with it ? This problem, dubbed fashion collocation, has almost been neglected by researchers due to the large uncertainty lies in fashion collocation and professional expertise required to address it. In this paper, we narrow down the well-collocated samples to be fashion images shared on fashion websites, with which we propose an end-to-end trainable deep mixed-category metric learning method to project well-collocated clothing items to lie close but items violating well-collocation far apart in the deep embedding space. Specifically, we simultaneously model the intra-category exclusiveness and cross-category inclusiveness of fashion collocation by feeding a set of well-collocated clothing items and corresponding bad-collocated clothing items to the deep neural network, further a hard-aware online exemplar mining strategy is designed to force the whole neural network to be trainable and learn discriminative features at the early and later training stages respectively. To motivate more research in fashion collocation, we collect a dataset of 0.2 million fashionably well-collocated images consisting of either on-body or off-body clothing items or accessories. Extensive experimental results show the feasibility and superiority of our method.

The pattern satisfiability is a fundamental problem for SPARQL. This paper provides a complete analysis of decidability/undecidability of satisfiability problems for SPARQL 1.1 patterns. A surprising result is the undecidability of satisfiability for SPARQL 1.1 patterns when only AND and MINUS are expressible. Also, it is shown that any fragment of SPARQL 1.1 without expressing both AND and MINUS is decidable. These results provide a guideline for future SPARQL query language design and implementation.

We investigate the relationship between conditional independence (CI) x ⊥  y | Z and the independence of two residuals x – E ( x | Z ) ⊥  –E ( y | Z ), where x and y are two random variables, and Z is a set of random variables. We show that if x, y and Z are generated by following linear structural equation model and all external influences follow Gaussian distributions, then x ⊥  y | Z if and only if x – E ( x | Z ) ⊥ y – E ( y | Z ). That is, the test of x ⊥  y | Z can be relaxed to a simpler unconditional independence test of x – E ( x | Z ) ⊥  y – E ( y | Z ). Furthermore, if all these external influences follow non-Gaussian distributions and the model satisfies structural faithfulness condition, then we have x ⊥  y | Z ⇔ x – E ( x | Z ) ⊥  y – E ( y | Z ). We apply the results above to the causal discovery problem, where the causal directions are generally determined by a set of V -structures and their consistent propagations, so CI test-based methods can return a set of Markov equivalence classes. We show that in linear non-Gaussian context, x – E ( x | Z ) ⊥  y – E ( y | Z ) ⇒ x – E ( x | Z ) ⊥  z or y – E ( y | Z ⊥  z (∀ z ∈  Z ) if Z is a minimal d -separator, which implies z causes x (or y ) if z directly connects to x (or y ). Therefore, we conclude that CIs have useful information for distinguishing Markov equivalence classes. In summary, compared with the existing discretization-based and kernel-based CI testing methods, the proposed method provides a simpler way to measure CI, which needs only one unconditional independence test and two regression operations. When being applied to causal discovery, it can find more causal relationships, which is experimentally validated.

Existential rules, a family of expressive ontology languages, inherit desired expressive and reasoning properties from both description logics and logic programming. On the other hand, forgetting is a well studied operation for ontology reuse, obfuscation and analysis. Yet it is challenging to establish a theory of forgetting for existential rules. In this paper, we lay the foundation for a theory of forgetting for existential rules by developing a novel notion of unfolding. In particular, we introduce a definition of forgetting for existential rules in terms of query answering and provide a characterisation of forgetting by the unfolding. A result of forgetting may not be expressible in existential rules, and we then capture the expressibility of forgetting by a variant of boundedness. While the expressibility is undecidable in general, we identify a decidable fragment. Finally, we provide an algorithm for forgetting in this fragment.

We define a consensus postulate in the propositional belief merging setting. In a nutshell, this postulate imposes the merged base to be consistent with the pieces of information provided by each agent involved in the merging process. The interplay of this new postulate with the IC postulates for belief merging is studied, and an incompatibility result is proved. The maximal sets of IC postulates which are consistent with the consensus postulate are exhibited. When satisfying some of the remaining IC postulates, consensus operators are shown to suffer from a weak inferential power. We then introduce two families of consensus operators having a better inferential power by setting aside some of these postulates.

Causal discovery without intervention is well recognized as a challenging yet powerful data analysis tool, boosting the development of other scientific areas, such as biology, astronomy, and social science. The major technical difficulty behind the observation-based causal discovery is to effectively and efficiently identify causes and effects from correlated variables given the existence of significant noises. Previous studies mostly employ two very different methodologies under Bayesian network framework, namely global likelihood maximization and locally complexity analysis over marginal distributions. While these approaches are effective in their respective problem domains, in this paper, we show that they can be combined to formulate a new global optimization model with local statistical significance, called structural equational likelihood framework (or SELF in short). We provide thorough analysis on the soundness of the model under mild conditions and present efficient heuristic-based algorithms for scalable model training. Empirical evaluations using XGBoost validate the superiority of our proposal over state-of-the-art solutions, on both synthetic and real world causal structures.

We propose AutoID, a human identification system that leverages the measurements from existing WiFi-enabled Internet of Things (IoT) devices and produces the identity estimation via a novel sparse representation learning technique. The key idea is to use the unique fine-grained gait patterns of each person revealed from the WiFi Channel State Information (CSI) measurements, technically referred to as shapelet signatures, as the "fingerprint" for human identification. For this purpose, a novel OpenWrt-based IoT platform is designed to collect CSI data from commercial IoT devices. More importantly, we propose a new optimization-based shapelet learning framework for tensors, namely Convex Clustered Concurrent Shapelet Learning (C3SL), which formulates the learning problem as a convex optimization. The global solution of C3SL can be obtained efficiently with a generalized gradient-based algorithm, and the three concurrent regularization terms reveal the inter-dependence and the clustering effect of the CSI tensor data. Extensive experiments are conducted in multiple real-world indoor environments, showing that AutoID achieves an average human identification accuracy of 91% from a group of 20 people. As a combination of novel sensing and learning platform, AutoID attains substantial progress towards a more accurate, cost-effective and sustainable human identification system for pervasive implementations.

Mechanisms for aggregating the preferences of agents in elections need to balance many different considerations, including efficiency, information elicited from agents, and manipulability. We consider the utilitarian social welfare of mechanisms for preference aggregation, measured by the distortion. We show that for a particular input format called threshold approval voting, where each agent is presented with an independently chosen threshold, there is a mechanism with nearly optimal distortion when the number of voters is large. Threshold mechanisms are potentially manipulable, but place a low informational burden on voters. We then consider truthful mechanisms. For the widely-studied class of ordinal mechanisms which elicit the rankings of candidates from each agent, we show that truthfulness essentially imposes no additional loss of welfare. We give truthful mechanisms with distortion O(√m log m) for k-winner elections, and distortion O(√m log m) when candidates have arbitrary costs, in elections with m candidates. These nearly match known lower bounds for ordinal mechanisms that ignore the strategic behavior. We further tighten these lower bounds and show that for truthful mechanisms our first upper bound is tight. Lastly, when agents decide between two candidates, we give tight bounds on the distortion for truthful mechanisms.

Multi-Entity Dependence Learning (MEDL) explores conditional correlations among multiple entities. The availability of rich contextual information requires a nimble learning scheme that tightly integrates with deep neural networks and has the ability to capture correlation structures among exponentially many outcomes. We propose MEDL_CVAE, which encodes a conditional multivariate distribution as a generating process. As a result, the variational lower bound of the joint likelihood can be optimized via a conditional variational auto-encoder and trained end-to-end on GPUs. Our MEDL_CVAE was motivated by two real-world applications in computational sustainability: one studies the spatial correlation among multiple bird species using the eBird data and the other models multi-dimensional landscape composition and human footprint in the Amazon rainforest with satellite images. We show that MEDL_CVAE captures rich dependency structures, scales better than previous methods, and further improves on the joint likelihood taking advantage of very large datasets that are beyond the capacity of previous methods.