David Poole

Matthew Dirks, David Poole

Neural networks are configured by choosing an architecture and hyperparameter values; doing so often involves expert intuition and hand-tuning to find a configuration that extrapolates well without overfitting. This paper considers automatic methods for configuring a neural network that extrapolates in time for the domain of visible and near-infrared (VNIR) spectroscopy. In particular, we study the effect of (a) selecting samples for validating configurations and (b) using ensembles. Most of the time, models are built of the past to predict the future. To encourage the neural network model to extrapolate, we consider validating model configurations on samples that are shifted in time similar to the test set. We experiment with three validation set choices: (1) a random sample of 1/3 of non-test data (the technique used in previous work), (2) using the latest 1/3 (sorted by time), and (3) using a semantically meaningful subset of the data. Hyperparameter optimization relies on the validation set to estimate test-set error, but neural network variance obfuscates the true error value. Ensemble averaging - computing the average across many neural networks - can reduce the variance of prediction errors. To test these methods, we do a comprehensive study of a held-out 2018 harvest season of mango fruit given VNIR spectra from 3 prior years. We find that ensembling improves the state-of-the-art model's variance and accuracy. Furthermore, hyperparameter optimization experiments - with and without ensemble averaging and with each validation set choice - show that when ensembling is combined with using the latest 1/3 of samples as the validation set, a neural network configuration is found automatically that is on par with the state-of-the-art.

Matthew Dirks, David Poole

We consider energy-dispersive X-ray Fluorescence (EDXRF) applications where the fundamental parameters method is impractical such as when instrument parameters are unavailable. For example, on a mining shovel or conveyor belt, rocks are constantly moving (leading to varying angles of incidence and distances) and there may be other factors not accounted for (like dust). Neural networks do not require instrument and fundamental parameters but training neural networks requires XRF spectra labelled with elemental composition, which is often limited because of its expense. We develop a neural network model that learns from limited labelled data and also benefits from domain knowledge by learning to invert a forward model. The forward model uses transition energies and probabilities of all elements and parameterized distributions to approximate other fundamental and instrument parameters. We evaluate the model and baseline models on a rock dataset from a lithium mineral exploration project. Our model works particularly well for some low-Z elements (Li, Mg, Al, and K) as well as some high-Z elements (Sn and Pb) despite these elements being outside the suitable range for common spectrometers to directly measure, likely owing to the ability of neural networks to learn correlations and non-linear relationships.

Seyed Mehran Kazemi, David Poole

Knowledge graphs contain knowledge about the world and provide a structured representation of this knowledge. Current knowledge graphs contain only a small subset of what is true in the world. Link prediction approaches aim at predicting new links for a knowledge graph given the existing links among the entities. Tensor factorization approaches have proved promising for such link prediction problems. Proposed in 1927, Canonical Polyadic (CP) decomposition is among the first tensor factorization approaches. CP generally performs poorly for link prediction as it learns two independent embedding vectors for each entity, whereas they are really tied. We present a simple enhancement of CP (which we call SimplE) to allow the two embeddings of each entity to be learned dependently. The complexity of SimplE grows linearly with the size of embeddings. The embeddings learned through SimplE are interpretable, and certain types of background knowledge can be incorporated into these embeddings through weight tying. We prove SimplE is fully expressive and derive a bound on the size of its embeddings for full expressivity. We show empirically that, despite its simplicity, SimplE outperforms several state-of-the-art tensor factorization techniques. SimplE's code is available on GitHub at https://github.com/Mehran-k/SimplE.

Bahare Fatemi, Seyed Mehran Kazemi, David Poole

Relational logistic regression (RLR) is a representation of conditional probability in terms of weighted formulae for modelling multi-relational data. In this paper, we develop a learning algorithm for RLR models. Learning an RLR model from data consists of two steps: 1- learning the set of formulae to be used in the model (a.k.a. structure learning) and learning the weight of each formula (a.k.a. parameter learning). For structure learning, we deploy Schmidt and Murphy's hierarchical assumption: first we learn a model with simple formulae, then more complex formulae are added iteratively only if all their sub-formulae have proven effective in previous learned models. For parameter learning, we convert the problem into a non-relational learning problem and use an off-the-shelf logistic regression learning algorithm from Weka, an open-source machine learning tool, to learn the weights. We also indicate how hidden features about the individuals can be incorporated into RLR to boost the learning performance. We compare our learning algorithm to other structure and parameter learning algorithms in the literature, and compare the performance of RLR models to standard logistic regression and RDN-Boost on a modified version of the MovieLens data-set.

David Poole

Artificial intelligence seems to be taking over the world with systems that model pixels, words, and phonemes. The world is arguably made up, not of pixels, words, and phonemes but of entities (objects, things, including events) with properties and relations among them. Surely we should model these, not the perception or description of them. You might suspect that concentrating on modeling words and pixels is because all of the (valuable) data in the world is in terms of text and images. If you look into almost any company you will find their most valuable data is in spreadsheets, databases and other relational formats. These are not the form that are studied in introductory machine learning, but are full of product numbers, student numbers, transaction numbers and other identifiers that can't be interpreted naively as numbers. The field that studies this sort of data has various names including relational learning, statistical relational AI, and many others. This paper explains why relational learning is not taking over the world -- except in a few cases with restricted relations -- and what needs to be done to bring it to it's rightful prominence.

Bahare Fatemi, Perouz Taslakian, David Vazquez et al.

Embedding-based methods for reasoning in knowledge hypergraphs learn a representation for each entity and relation. Current methods do not capture the procedural rules underlying the relations in the graph. We propose a simple embedding-based model called ReAlE that performs link prediction in knowledge hypergraphs (generalized knowledge graphs) and can represent high-level abstractions in terms of relational algebra operations. We show theoretically that ReAlE is fully expressive and provide proofs and empirical evidence that it can represent a large subset of the primitive relational algebra operations, namely renaming, projection, set union, selection, and set difference. We also verify experimentally that ReAlE outperforms state-of-the-art models in knowledge hypergraph completion, and in representing each of these primitive relational algebra operations. For the latter experiment, we generate a synthetic knowledge hypergraph, for which we design an algorithm based on the Erdos-R'enyi model for generating random graphs.

Matthew Dirks, David Poole

Many evaluation methods exist, each for a particular prediction task, and there are a number of prediction tasks commonly performed including classification and regression. In binarised regression, binary decisions are generated from a learned regression model (or real-valued dependent variable), which is useful when the division between instances that should be predicted positive or negative depends on the utility. For example, in mining, the boundary between a valuable rock and a waste rock depends on the market price of various metals, which varies with time. This paper proposes impact curves to evaluate binarised regression with instance-varying costs, where some instances are much worse to be classified as positive (or negative) than other instances; e.g., it is much worse to throw away a high-grade gold rock than a medium-grade copper-ore rock, even if the mine wishes to keep both because both are profitable. We show how to construct an impact curve for a variety of domains, including examples from healthcare, mining, and entertainment. Impact curves optimize binary decisions across all utilities of the chosen utility function, identify the conditions where one model may be favoured over another, and quantitatively assess improvement between competing models.

Ainaz Hajimoradlou, Gioachino Roberti, David Poole

Landslides, movement of soil and rock under the influence of gravity, are common phenomena that cause significant human and economic losses every year. Experts use heterogeneous features such as slope, elevation, land cover, lithology, rock age, and rock family to predict landslides. To work with such features, we adapted convolutional neural networks to consider relative spatial information for the prediction task. Traditional filters in these networks either have a fixed orientation or are rotationally invariant. Intuitively, the filters should orient uphill, but there is not enough data to learn the concept of uphill; instead, it can be provided as prior knowledge. We propose a model called Locally Aligned Convolutional Neural Network, LACNN, that follows the ground surface at multiple scales to predict possible landslide occurrence for a single point. To validate our method, we created a standardized dataset of georeferenced images consisting of the heterogeneous features as inputs, and compared our method to several baselines, including linear regression, a neural network, and a convolutional network, using log-likelihood error and Receiver Operating Characteristic curves on the test set. Our model achieves 2-7% improvement in terms of accuracy and 2-15% boost in terms of log likelihood compared to the other proposed baselines.

Bahare Fatemi, Perouz Taslakian, David Vazquez et al.

Knowledge graphs store facts using relations between two entities. In this work, we address the question of link prediction in knowledge hypergraphs where relations are defined on any number of entities. While techniques exist (such as reification) that convert non-binary relations into binary ones, we show that current embedding-based methods for knowledge graph completion do not work well out of the box for knowledge graphs obtained through these techniques. To overcome this, we introduce HSimplE and HypE, two embedding-based methods that work directly with knowledge hypergraphs. In both models, the prediction is a function of the relation embedding, the entity embeddings and their corresponding positions in the relation. We also develop public datasets, benchmarks and baselines for hypergraph prediction and show experimentally that the proposed models are more effective than the baselines.

Bahare Fatemi, Siamak Ravanbakhsh, David Poole

Knowledge graphs are used to represent relational information in terms of triples. To enable learning about domains, embedding models, such as tensor factorization models, can be used to make predictions of new triples. Often there is background taxonomic information (in terms of subclasses and subproperties) that should also be taken into account. We show that existing fully expressive (a.k.a. universal) models cannot provably respect subclass and subproperty information. We show that minimal modifications to an existing knowledge graph completion method enables injection of taxonomic information. Moreover, we prove that our model is fully expressive, assuming a lower-bound on the size of the embeddings. Experimental results on public knowledge graphs show that despite its simplicity our approach is surprisingly effective.

Nandini Ramanan, Gautam Kunapuli, Tushar Khot et al.

We consider the problem of learning Relational Logistic Regression (RLR). Unlike standard logistic regression, the features of RLRs are first-order formulae with associated weight vectors instead of scalar weights. We turn the problem of learning RLR to learning these vector-weighted formulae and develop a learning algorithm based on the recently successful functional-gradient boosting methods for probabilistic logic models. We derive the functional gradients and show how weights can be learned simultaneously in an efficient manner. Our empirical evaluation on standard and novel data sets demonstrates the superiority of our approach over other methods for learning RLR.

Bahare Fatemi, Seyed Mehran Kazemi, David Poole

Consider the following problem: given a database of records indexed by names (e.g., name of companies, restaurants, businesses, or universities) and a new name, determine whether the new name is in the database, and if so, which record it refers to. This problem is an instance of record linkage problem and is a challenging problem because people do not consistently use the official name, but use abbreviations, synonyms, different order of terms, different spelling of terms, short form of terms, and the name can contain typos or spacing issues. We provide a probabilistic model using relational logistic regression to find the probability of each record in the database being the desired record for a given query and find the best record(s) with respect to the probabilities. Building on term-matching and translational approaches for search, our model addresses many of the aforementioned challenges and provides good results when existing baselines fail. Using the probabilities outputted by the model, we can automate the search process for a portion of queries whose desired documents get a probability higher than a trust threshold. We evaluate our model on a large real-world dataset from a telecommunications company and compare it to several state-of-the-art baselines. The obtained results show that our model is a promising probabilistic model for record linkage for names. We also test if the knowledge learned by our model on one domain can be effectively transferred to a new domain. For this purpose, we test our model on an unseen test set from the business names of the secondString dataset. Promising results show that our model can be effectively applied to unseen datasets. Finally, we study the sensitivity of our model to the statistics of datasets.

Seyed Mehran Kazemi, David Poole

Statistical relational AI (StarAI) aims at reasoning and learning in noisy domains described in terms of objects and relationships by combining probability with first-order logic. With huge advances in deep learning in the current years, combining deep networks with first-order logic has been the focus of several recent studies. Many of the existing attempts, however, only focus on relations and ignore object properties. The attempts that do consider object properties are limited in terms of modelling power or scalability. In this paper, we develop relational neural networks (RelNNs) by adding hidden layers to relational logistic regression (the relational counterpart of logistic regression). We learn latent properties for objects both directly and through general rules. Back-propagation is used for training these models. A modular, layer-wise architecture facilitates utilizing the techniques developed within deep learning community to our architecture. Initial experiments on eight tasks over three real-world datasets show that RelNNs are promising models for relational learning.

Seyed Mehran Kazemi, Bahare Fatemi, Alexandra Kim et al.

Relational probabilistic models have the challenge of aggregation, where one variable depends on a population of other variables. Consider the problem of predicting gender from movie ratings; this is challenging because the number of movies per user and users per movie can vary greatly. Surprisingly, aggregation is not well understood. In this paper, we show that existing relational models (implicitly or explicitly) either use simple numerical aggregators that lose great amounts of information, or correspond to naive Bayes, logistic regression, or noisy-OR that suffer from overconfidence. We propose new simple aggregators and simple modifications of existing models that empirically outperform the existing ones. The intuition we provide on different (existing or new) models and their shortcomings plus our empirical findings promise to form the foundation for future representations.

Seyed Mehran Kazemi, Angelika Kimmig, Guy Van den Broeck et al.

In recent work, we proved that the domain recursion inference rule makes domain-lifted inference possible on several relational probability models (RPMs) for which the best known time complexity used to be exponential. We also identified two classes of RPMs for which inference becomes domain lifted when using domain recursion. These two classes subsume the largest lifted classes that were previously known. In this paper, we show that domain recursion can also be applied to models with existential quantifiers. Currently, all lifted inference algorithms assume that existential quantifiers have been removed in pre-processing by Skolemization. We show that besides introducing potentially inconvenient negative weights, Skolemization may increase the time complexity of inference. We give two example models where domain recursion can replace Skolemization, avoids the need for dealing with negative numbers, and reduces the time complexity of inference. These two examples may be interesting from three theoretical aspects: 1- they provide a better and deeper understanding of domain recursion and, in general, (lifted) inference, 2- they may serve as evidence that there are larger classes of models for which domain recursion can satisfyingly replace Skolemization, and 3- they may serve as evidence that better Skolemization techniques exist.

Seyed Mehran Kazemi, Angelika Kimmig, Guy Van den Broeck et al.

Statistical relational models provide compact encodings of probabilistic dependencies in relational domains, but result in highly intractable graphical models. The goal of lifted inference is to carry out probabilistic inference without needing to reason about each individual separately, by instead treating exchangeable, undistinguished objects as a whole. In this paper, we study the domain recursion inference rule, which, despite its central role in early theoretical results on domain-lifted inference, has later been believed redundant. We show that this rule is more powerful than expected, and in fact significantly extends the range of models for which lifted inference runs in time polynomial in the number of individuals in the domain. This includes an open problem called S4, the symmetric transitivity model, and a first-order logic encoding of the birthday paradox. We further identify new classes S2FO2 and S2RU of domain-liftable theories, which respectively subsume FO2 and recursively unary theories, the largest classes of domain-liftable theories known so far, and show that using domain recursion can achieve exponential speedup even in theories that cannot fully be lifted with the existing set of inference rules.

Seyed Mehran Kazemi, David Poole

First-order knowledge compilation techniques have proven efficient for lifted inference. They compile a relational probability model into a target circuit on which many inference queries can be answered efficiently. Early methods used data structures as their target circuit. In our KR-2016 paper, we showed that compiling to a low-level program instead of a data structure offers orders of magnitude speedup, resulting in the state-of-the-art lifted inference technique. In this paper, we conduct experiments to address two questions regarding our KR-2016 results: 1- does the speedup come from more efficient compilation or more efficient reasoning with the target circuit?, and 2- why are low-level programs more efficient target circuits than data structures?

Ramon Lopez de Mantaras, David Poole

This is the Proceedings of the Tenth Conference on Uncertainty in Artificial Intelligence, which was held in Seattle, WA, July 29-31, 1994