Encoding structure in holographic reduced representations

Vector Symbolic Architectures (VSAs) such as Holographic Reduced Representations (HRRs) are computational associative memories used by cognitive psychologists to model behavioural and neurological aspects of human memory. We present a novel analysis of the mathematics of VSAs and a novel technique for representing data in HRRs. Encoding and decoding in VSAs can be characterized by Latin squares. Successful encoding requires the structure of the data to be orthogonal to the structure of the Latin squares. However, HRRs can successfully encode vectors of locally structured data if vectors are shuffled. Shuffling results are illustrated using images, but are applicable to any non-random data. The ability to use locally structured vectors provides a technique for detailed modelling of stimuli in HRR models.

Holographic Factorization Machines for Recommendation

Factorization Machines (FMs) are a class of popular algorithms that have been widely adopted for collaborative filtering and recommendation tasks. FMs are characterized by its usage of the inner product of factorized parameters to model pairwise feature interactions, making it highly expressive and powerful. This paper proposes Holographic Factorization Machines (HFM), a new novel method of enhancing the representation capability of FMs without increasing its parameter size. Our approach replaces the inner product in FMs with holographic reduced representations (HRRs), which are theoretically motivated by associative retrieval and compressed outer products. Empirically, we found that this leads to consistent improvements over vanilla FMs by up to 4% improvement in terms of mean squared error, with improvements larger at smaller parameterization. Additionally, we propose a neural adaptation of HFM which enhances its capability to handle nonlinear structures. We conduct extensive experiments on nine publicly available datasets for collaborative filtering with explicit feedback. HFM achieves state-of-theart performance on all nine, outperforming strong competitors such as Attentional Factorization Machines (AFM) and Neural Matrix Factorization (NeuMF).

Vector-Derived Transformation Binding: An Improved Binding Operation for Deep Symbol-Like Processing in Neural Networks

We present a new binding operation, vector-derived transformation binding (VTB), for use in vector symbolic architectures (VSA). The performance of VTB is compared to circular convolution, used in holographic reduced representations (HRRs), in terms of list and stack encoding capacity. A special focus is given to the possibility of a neural implementation by the means of the Neural Engineering Framework (NEF). While the scaling of required neural resources is slightly worse for VTB, it is found to be on par with circular convolution for list encoding and better for encoding of stacks. Furthermore, VTB influences the vector length less, which also benefits a neural implementation. Consequently, we argue that VTB is an improvement over HRRs for neurally implemented VSAs.

EMPIRICAL ANALYSIS OF THE EFFECT OF DIMENSION REDUCTION AND WORD ORDER ON SEMANTIC VECTORS

The aim of this paper is to provide a comparison of various algorithms and parameters to build reduced semantic spaces. The effect of dimension reduction, the stability of the representation and the effect of word order are examined in the context of the five algorithms bearing on semantic vectors: Random projection (RP), singular value decomposition (SVD), non-negative matrix factorization (NMF), permutations and holographic reduced representations (HRR). The quality of semantic representation was tested by means of synonym finding task using the TOEFL test on the TASA corpus. Dimension reduction was found to improve the quality of semantic representation but it is hard to find the optimal parameter settings. Even though dimension reduction by RP was found to be more generally applicable than SVD, the semantic vectors produced by RP are somewhat unstable. The effect of encoding word order into the semantic vector representation via HRR did not lead to any increase in scores over vectors constructed from word co-occurrence in context information. In this regard, very small context windows resulted in better semantic vectors for the TOEFL test.

Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning

Distributed representations were often criticized as inappropriate for encoding of data with a complex structure. However Plate's holographic reduced representations and Kanerva's binary spatter codes are recent schemes that allow on-the-fly encoding of nested compositional structures by real-valued or dense binary vectors of fixed dimensionality. In this article we consider procedures of the context-dependent thinning developed for representation of complex hierarchical items in the architecture of associative-projective neural networks. These procedures provide binding of items represented by sparse binary codevectors (with low probability of 1s). Such an encoding is biologically plausible and allows a high storage capacity of distributed associative memory where the codevectors may be stored. In contrast to known binding procedures, context-dependent thinning preserves the same low density (or sparseness) of the bound codevector for a varied number of component codevectors. Besides, a bound codevector is similar not only to another one with similar component codevectors (as in other schemes) but also to the component codevectors themselves. This allows the similarity of structures to be estimated by the overlap of their codevectors, without retrieval of the component codevectors. This also allows easy retrieval of the component codevectors. Examples of algorithmic and neural network implementations of the thinning procedures are considered. We also present representation examples for various types of nested structured data (propositions using role filler and predicate arguments schemes, trees, and directed acyclic graphs) using sparse codevectors of fixed dimension. Such representations may provide a fruitful alternative to the symbolic representations of traditional artificial intelligence as well as to the localist and microfeature-based connectionist representations.

Chunks, bindings, STAR, and Holographic Reduced Representations

Much of Halford et al.'s discussion of vector models for representing relations concerns the perceived inadequacies of alternative methods with respect to chunking, binding, systematicity, and resource requirements. Vector-based models for storing relations are in their infancy, however, and the relative merits of different schemes are not so clearly in favor of their STAR scheme as Halford et al. portray.