Search

Understanding node representations in graph-based models is crucial for uncovering biases ,diagnosing errors, and building trust in model decisions. However, previous work on explainable AI for node representations has primarily emphasized explanations (reasons for model predictions) rather than interpretations (mapping representations to understandable concepts). Furthermore, the limited research that focuses on interpretation lacks validation, and thus the reliability of such methods is unclear. We address this gap by proposing a novel interpretation method-Node Coherence Rate for Representation Interpretation (NCI)-which quantifies how well different node relations are captured in node representations. We also propose a novel method (IME) to evaluate the accuracy of different interpretation methods. Our experimental results demonstrate that NCI reduces the error of the previous best approach by an average of 39%. We then apply NCI to derive insights about the node representations produced by several graph-based methods and assess their quality in unsupervised settings.

Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or weaker models (possibly due to latency or cost gains), prompts need to be updated to re-optimize the task performance. We propose Concept Distillation (CD), an automatic prompt optimization technique for enhancing weaker models on complex tasks. CD involves: (1) collecting mistakes made by weak models with a base prompt (initialization), (2) using a strong model to generate reasons for these mistakes and create rules/concepts for weak models (induction), and (3) filtering these rules based on validation set performance and integrating them into the base prompt (deduction/verification). We evaluated CD on NL2Code and mathematical reasoning tasks, observing significant performance boosts for small and weaker language models. Notably, Mistral-7B's accuracy on Multi-Arith increased by 20%, and Phi-3-mini-3.8B's accuracy on HumanEval rose by 34%. Compared to other automated methods, CD offers an effective, cost-efficient strategy for improving weak models' performance on complex tasks and enables seamless workload migration across different language models without compromising performance., Comment: 13 pages, 8 figures, conference

Random Projections have been widely used to generate embeddings for various graph learning tasks due to their computational efficiency. The majority of applications have been justified through the Johnson-Lindenstrauss Lemma. In this paper, we take a step further and investigate how well dot product and cosine similarity are preserved by random projections when these are applied over the rows of the graph matrix. Our analysis provides new asymptotic and finite-sample results, identifies pathological cases, and tests them with numerical experiments. We specialize our fundamental results to a ranking application by computing the probability of random projections flipping the node ordering induced by their embeddings. We find that, depending on the degree distribution, the method produces especially unreliable embeddings for the dot product, regardless of whether the adjacency or the normalized transition matrix is used. With respect to the statistical noise introduced by random projections, we show that cosine similarity produces remarkably more precise approximations.

Recent advances in computational models of signal propagation and routing in the human brain have underscored the critical role of white matter structure. A complementary approach has utilized the framework of network control theory to better understand how white matter constrains the manner in which a region or set of regions can direct or control the activity of other regions. Despite the potential for both of these approaches to enhance our understanding of the role of network structure in brain function, little work has sought to understand the relations between them. Here, we seek to explicitly bridge computational models of communication and principles of network control in a conceptual review of the current literature. By drawing comparisons between communication and control models in terms of the level of abstraction, the dynamical complexity, the dependence on network attributes, and the interplay of multiple spatiotemporal scales, we highlight the convergence of and distinctions between the two frameworks. Based on the understanding of the intertwined nature of communication and control in human brain networks, this work provides an integrative perspective for the field and outlines exciting directions for future work., Comment: 23 pages, 4 figures

In this paper, we consider the problem of tuning the edge weights of a networked system described by linear time-invariant dynamics. We assume that the topology of the underlying network is fixed and that the set of feasible edge weights is a given polytope. In this setting, we first consider a feasibility problem consisting of tuning the edge weights such that certain controllability properties are satisfied. The particular controllability properties under consideration are (i) a lower bound on the smallest eigenvalue of the controllability Gramian, which is related to the worst-case energy needed to control the system, and (ii) an upper bound on the trace of the Gramian inverse, which is related to the average control energy. In both cases, the edge-tuning problem can be stated as a feasibility problem involving bilinear matrix equalities, which we approach using a sequence of convex relaxations. Furthermore, we also address a design problem consisting of finding edge weights able to satisfy the aforementioned controllability constraints while seeking to minimize a cost function of the edge weights, which we assume to be convex. In particular, we consider a sparsity-promoting cost function aiming to penalize the number of edges whose weights are modified. Finally, we verify our results with numerical simulations over many random network realizations as well as with an IEEE 14-bus power system topology.

Understanding the relationship between the dynamics of neural processes and the anatomical substrate of the brain is a central question in neuroscience. On the one hand, modern neuroimaging technologies, such as diffusion tensor imaging, can be used to construct structural graphs representing the architecture of white matter streamlines linking cortical and subcortical structures. On the other hand, temporal patterns of neural activity can be used to construct functional graphs representing temporal correlations between brain regions. Although some studies provide evidence that whole-brain functional connectivity is shaped by the underlying anatomy, the observed relationship between function and structure is weak, and the rules by which anatomy constrains brain dynamics remain elusive. In this article, we introduce a methodology to predict with high accuracy the functional connectivity of a subject at rest from his or her structural graph. Using our methodology, we are able to systematically unveil the role of structural paths in the formation of functional correlations. Furthermore, in our empirical evaluations, we observe that the eigen-modes of the predicted functional connectivity are aligned with activity patterns associated with different cognitive systems. Our work offers the potential to infer properties of brain dynamics in clinical or developmental populations with low tolerance for functional neuroimaging.