Lung cancer screening with computed tomography (CT) scans can effectively improve the survival rate through the early detection of lung cancer, which typically identified in the form of pulmonary nodules. Multiple sequential CT images are helpful to determine nodule malignancy and play a significant role to detect lung cancers. It is crucial to develop effective lung cancer classification algorithms to achieve accurate results from multiple images without nodule location annotations, which can free radiologists from the burden of labeling nodule locations before predicting malignancy. In this study, we proposed the sequential multi-instance learning (SMILE) framework to predict high-risk lung cancer patients with multiple CT scans. SMILE included two steps. The first step was nodule instance generation. We employed the nodule detection algorithm with image category transformation to identify nodule instance locations within the entire lung images. The second step was nodule malignancy prediction. Models were supervised by patient-level annotations, without the exact locations of nodules. We embedded multi-instance learning with temporal feature extraction into a fusion framework, which effectively promoted the classification performance. SMILE was evaluated by five-fold cross-validation on a 925-patient dataset (182 malignant, 743 benign). Every patient had three CT scans, of which the interval period was about one year. Experimental results showed the potential of SMILE to free radiologists from labeling nodule locations. The source code will be available at https://github.com/wyzhao27/SMILE.

Probabilistic Sentential Decision Diagrams (PSDDs) provide efficient methods for modeling and reasoning with probability distributions in the presence of massive logical constraints. PSDDs can also be synthesized from graphical models such as Bayesian networks (BNs) therefore offering a new set of tools for performing inference on these models (in time linear in the PSDD size). Despite these favorable characteristics of PSDDs, we have found multiple challenges in PSDD’s FPGA acceleration. Problems include limited parallelism, data dependency, and small pipeline iterations. In this article, we propose several optimization techniques to solve these issues with novel pipeline scheduling and parallelization schemes. We designed the PSDD kernel with a high-level synthesis (HLS) tool for ease of implementation and verified it on the Xilinx Alveo U250 board. Experimental results show that our methods improve the baseline FPGA HLS implementation performance by 2,200X and the multicore CPU implementation by 20X. The proposed design also outperforms state-of-the-art BN and Sum Product Network (SPN) accelerators that store the graph information in memory.

Structured Bayesian networks (SBNs) are a recently proposed class of probabilistic graphical models which integrate background knowledge in two forms: conditional independence constraints and Boolean domain constraints. In this paper, we propose the first exact inference algorithm for SBNs, based on compiling a given SBN to a Probabilistic Sentential Decision Diagram (PSDD). We further identify a tractable subclass of SBNs, which have PSDDs of polynomial size. These SBNs yield a tractable model of route distributions, whose structure can be learned from GPS data, using a simple algorithm that we propose. Empirically, we demonstrate the utility of our inference algorithm, showing that it can be an order-ofmagnitude more efficient than more traditional approaches to exact inference. We demonstrate the utility of our learning algorithm, showing that it can learn more accurate models and classifiers from GPS data.

Testing Bayesian Networks (TBNs) were introduced recently to represent a set of distributions, one of which is selected based on the given evidence and used for reasoning. TBNs are more expressive than classical Bayesian Networks (BNs): Marginal queries correspond to multi-linear functions in BNs and to piecewise multi-linear functions in TBNs. Moreover, TBN queries are universal approximators, like neural networks. In this paper, we study conditional independence in TBNs, showing that it can be inferred from d-separation as in BNs. We also study the role of TBN expressiveness and independence in dealing with the problem of learning with incomplete models (i.e., ones that miss nodes or edges from the data-generating model). Finally, we illustrate our results on a number of concrete examples, including a case study on Hidden Markov Models.

Probabilistic Sentential Decision Diagrams (PSDDs) have been proposed for learning tractable probability distributions from a combination of data and background knowledge (in the form of Boolean constraints). In this paper, we propose a variant on PSDDs, called conditional PSDDs, for representing a family of distributions that are conditioned on the same set of variables. Conditional PSDDs can also be learned from a combination of data and (modular) background knowledge. We use conditional PSDDs to define a more structured version of Bayesian networks, in which nodes can have an exponential number of states, hence expanding the scope of domains where Bayesian networks can be applied. Compared to classical PSDDs, the new representation exploits the independencies captured by a Bayesian network to decompose the learning process into localized learning tasks, which enables the learning of better models while using less computation. We illustrate the promise of conditional PSDDs and structured Bayesian networks empirically, and by providing a case study to the modeling of distributions over routes on a map.

Recently, the Probabilistic Sentential Decision Diagram (PSDD) has been proposed as a framework for systematically inducing and learning distributions over structured objects, including combinatorial objects such as permutations and rankings, paths and matchings on a graph, etc. In this paper, we study the scalability of such models in the context of representing and learning distributions over routes on a map. In particular, we introduce the notion of a hierarchical route distribution and show how they can be leveraged to construct tractable PSDDs over route distributions, allowing them to scale to larger maps. We illustrate the utility of our model empirically, in a route prediction task, showing how accuracy can be increased significantly compared to Markov models.

We consider the problem of learning Bayesian networks optimally, when subject to background knowledge in the form of ancestral constraints. Our approach is based on a recently proposed framework for optimal structure learning based on non-decomposable scores, which is general enough to accommodate ancestral constraints. The proposed framework exploits oracles for learning structures using decomposable scores, which cannot accommodate ancestral constraints since they are non-decomposable. We show how to empower these oracles by passing them decomposable constraints that they can handle, which are inferred from ancestral constraints that they cannot handle. Empirically, we demonstrate that our approach can be orders-of-magnitude more efficient than alternative frameworks, such as those based on integer linear programming.

We consider tractable representations of probability distributions and the polytime operations they support. In particular, we consider a recently proposed arithmetic circuit representation, the Probabilistic Sentential Decision Diagram (PSDD). We show that PSDD supports a polytime multiplication operator, while they do not support a polytime operator for summing-out variables. A polytime multiplication operator make PSDDs suitable for a broader class of applications compared to arithmetic circuits, which do not in general support multiplication. As one example, we show that PSDD multiplication leads to a very simple but effective compilation algorithm for probabilistic graphical models: represent each model factor as a PSDD, and then multiply them.