arXiv subjects

Michael Rabbat

Publications and source records attributed to Michael Rabbat.

At least 73 records · Page 4Linked to original sources

arXiv2016

Graph reconstruction from the observation of diffused signals

Signal processing on graphs has received a lot of attention in the recent years. A lot of techniques have arised, inspired by classical signal processing ones, to allow studying signals on any kind of graph. A common aspect of these technique is that they require a graph correctly modeling the studied support to explain the signals that are observed on it. However, in many cases, such a graph is unavailable or has no real physical existence. An example of this latter case is a set of sensors randomly thrown in a field which obviously observe related information. To study such signals, there is no intuitive choice for a support graph. In this document, we address the problem of inferring a graph structure from the observation of signals, under the assumption that they were issued of the diffusion of initially i.i.d. signals. To validate our approach, we design an experimental protocol, in which we diffuse signals on a known graph. Then, we forget the graph, and show that we are able to retrieve it very precisely from the only knowledge of the diffused signals.

cs.IT↗

arXiv2016

Toward An Uncertainty Principle For Weighted Graphs

The uncertainty principle states that a signal cannot be localized both in time and frequency. With the aim of extending this result to signals on graphs, Agaskar&Lu introduce notions of graph and spectral spreads. They show that a graph uncertainty principle holds for some families of unweighted graphs. This principle states that a signal cannot be simultaneously localized both in graph and spectral domains. In this paper, we aim to extend their work to weighted graphs. We show that a naive extension of their definitions leads to inconsistent results such as discontinuity of the graph spread when regarded as a function of the graph structure. To circumvent this problem, we propose another definition of graph spread that relies on an inverse similarity matrix. We also discuss the choice of the distance function that appears in this definition. Finally, we compute and plot uncertainty curves for families of weighted graphs.

cs.DM↗

arXiv2016

Multisensor CPHD filter

The single sensor probability hypothesis density (PHD) and cardinalized probability hypothesis density (CPHD) filters have been developed in the literature using the random finite set framework. The existing multisensor extensions of these filters have limitations such as sensor order dependence, numerical instability or high computational requirements. In this paper we derive update equations for the multisensor CPHD filter. The multisensor PHD filter is derived as a special case. Exact implementation of the multisensor CPHD involves sums over all partitions of the measurements from different sensors and is thus intractable. We propose a computationally tractable approximation which combines a greedy measurement partitioning algorithm with the Gaussian mixture representation of the PHD. Our greedy approximation method allows the user to control the tradeoff between computational overhead and approximation accuracy.

stat.ME↗

arXiv2016

Qualities and Inequalities in Online Social Networks through the Lens of the Generalized Friendship Paradox

The friendship paradox is the phenomenon that in social networks, people on average have fewer friends than their friends do. The generalized friendship paradox is an extension to attributes other than the number of friends. The friendship paradox and its generalized version have gathered recent attention due to the information they provide about network structure and local inequalities. In this paper, we propose several measures of nodal qualities which capture different aspects of their activities and influence in online social networks. Using these measures we analyse the prevalence of the generalized friendship paradox over Twitter and we report high levels of prevalence (up to over 90\% of nodes). We contend that this prevalence of the friendship paradox and its generalized version arise because of the hierarchical nature of the connections in the network. This hierarchy is nested as opposed to being star-like. We conclude that these paradoxes are collective phenomena not created merely by a minority of well-connected or high-attribute nodes. Moreover, our results show that a large fraction of individuals can experience the generalized friendship paradox even in the absence of a significant correlation between degrees and attributes.

cs.SI↗

arXiv2014

Combating Corrupt Messages in Sparse Clustered Associative Memories

In this paper we analyze and extend the neural network based associative memory proposed by Gripon and Berrou. This associative memory resembles the celebrated Willshaw model with an added partite cluster structure. In the literature, two retrieving schemes have been proposed for the network dynamics, namely sum-of-sum and sum-of-max. They both offer considerably better performance than Willshaw and Hopfield networks, when comparable retrieval scenarios are considered. Former discussions and experiments concentrate on the erasure scenario, where a partial message is used as a probe to the network, in the hope of retrieving the full message. In this regard, sum-of-max outperforms sum-of-sum in terms of retrieval rate by a large margin. However, we observe that when noise and errors are present and the network is queried by a corrupt probe, sum-of-max faces a severe limitation as its stringent activation rule prevents a neuron from reviving back into play once deactivated. In this manuscript, we categorize and analyze different error scenarios so that both the erasure and the corrupt scenarios can be treated consistently. We make an amendment to the network structure to improve the retrieval rate, at the cost of an extra scalar per neuron. Afterwards, five different approaches are proposed to deal with corrupt probes. As a result, we extend the network capability, and also increase the robustness of the retrieving procedure. We then experimentally compare all these proposals and discuss pros and cons of each approach under different types of errors. Simulation results show that if carefully designed, the network is able to preserve both a high retrieval rate and a low running time simultaneously, even when queried by a corrupt probe.

cs.NE↗

arXiv2014

Storing sequences in binary tournament-based neural networks

An extension to a recently introduced architecture of clique-based neural networks is presented. This extension makes it possible to store sequences with high efficiency. To obtain this property, network connections are provided with orientation and with flexible redundancy carried by both spatial and temporal redundancy, a mechanism of anticipation being introduced in the model. In addition to the sequence storage with high efficiency, this new scheme also offers biological plausibility. In order to achieve accurate sequence retrieval, a double layered structure combining hetero-association and auto-association is also proposed.

cs.NE↗

arXiv2014

Active Learning of Multiple Source Multiple Destination Topologies

We consider the problem of inferring the topology of a network with $M$ sources and $N$ receivers (hereafter referred to as an $M$-by-$N$ network), by sending probes between the sources and receivers. Prior work has shown that this problem can be decomposed into two parts: first, infer smaller subnetwork components (i.e., $1$-by-$N$'s or $2$-by-$2$'s) and then merge these components to identify the $M$-by-$N$ topology. In this paper, we focus on the second part, which had previously received less attention in the literature. In particular, we assume that a $1$-by-$N$ topology is given and that all $2$-by-$2$ components can be queried and learned using end-to-end probes. The problem is which $2$-by-$2$'s to query and how to merge them with the given $1$-by-$N$, so as to exactly identify the $2$-by-$N$ topology, and optimize a number of performance metrics, including the number of queries (which directly translates into measurement bandwidth), time complexity, and memory usage. We provide a lower bound, $\lceil \frac{N}{2} \rceil$, on the number of $2$-by-$2$'s required by any active learning algorithm and propose two greedy algorithms. The first algorithm follows the framework of multiple hypothesis testing, in particular Generalized Binary Search (GBS), since our problem is one of active learning, from $2$-by-$2$ queries. The second algorithm is called the Receiver Elimination Algorithm (REA) and follows a bottom-up approach: at every step, it selects two receivers, queries the corresponding $2$-by-$2$, and merges it with the given $1$-by-$N$; it requires exactly $N-1$ steps, which is much less than all $\binom{N}{2}$ possible $2$-by-$2$'s. Simulation results over synthetic and realistic topologies demonstrate that both algorithms correctly identify the $2$-by-$N$ topology and are near-optimal, but REA is more efficient in practice.

cs.NI↗

arXiv2013

Improving Sparse Associative Memories by Escaping from Bogus Fixed Points

The Gripon-Berrou neural network (GBNN) is a recently invented recurrent neural network embracing a LDPC-like sparse encoding setup which makes it extremely resilient to noise and errors. A natural use of GBNN is as an associative memory. There are two activation rules for the neuron dynamics, namely sum-of-sum and sum-of-max. The latter outperforms the former in terms of retrieval rate by a huge margin. In prior discussions and experiments, it is believed that although sum-of-sum may lead the network to oscillate, sum-of-max always converges to an ensemble of neuron cliques corresponding to previously stored patterns. However, this is not entirely correct. In fact, sum-of-max often converges to bogus fixed points where the ensemble only comprises a small subset of the converged state. By taking advantage of this overlooked fact, we can greatly improve the retrieval rate. We discuss this particular issue and propose a number of heuristics to push sum-of-max beyond these bogus fixed points. To tackle the problem directly and completely, a novel post-processing algorithm is also developed and customized to the structure of GBNN. Experimental results show that the new algorithm achieves a huge performance boost in terms of both retrieval rate and run-time, compared to the standard sum-of-max and all the other heuristics.

cs.NE↗

arXiv2013

Maximum Likelihood Associative Memories

Associative memories are structures that store data in such a way that it can later be retrieved given only a part of its content -- a sort-of error/erasure-resilience property. They are used in applications ranging from caches and memory management in CPUs to database engines. In this work we study associative memories built on the maximum likelihood principle. We derive minimum residual error rates when the data stored comes from a uniform binary source. Second, we determine the minimum amount of memory required to store the same data. Finally, we bound the computational complexity for message retrieval. We then compare these bounds with two existing associative memory architectures: the celebrated Hopfield neural networks and a neural network architecture introduced more recently by Gripon and Berrou.

cs.IT↗

arXiv2013

Reconstructing a Graph from Path Traces

This paper considers the problem of inferring the structure of a network from indirect observations. Each observation (a "trace") is the unordered set of nodes which are activated along a path through the network. Since a trace does not convey information about the order of nodes within the path, there are many feasible orders for each trace observed, and thus the problem of inferring the network from traces is, in general, illposed. We propose and analyze an algorithm which inserts edges by ordering each trace into a path according to which pairs of nodes in the path co-occur most frequently in the observations. When all traces involve exactly 3 nodes, we derive necessary and sufficient conditions for the reconstruction algorithm to exactly recover the graph. Finally, for a family of random graphs, we present expressions for reconstruction error probabilities (false discoveries and missed detections).

cs.DS↗

arXiv2012

Forwarding Without Repeating: Efficient Rumor Spreading in Bounded-Degree Graphs

We study a gossip protocol called forwarding without repeating (FWR). The objective is to spread multiple rumors over a graph as efficiently as possible. FWR accomplishes this by having nodes record which messages they have forwarded to each neighbor, so that each message is forwarded at most once to each neighbor. We prove that FWR spreads a rumor over a strongly connected digraph, with high probability, in time which is within a constant factor of optimal for digraphs with bounded out-degree. Moreover, on digraphs with bounded out-degree and bounded number of rumors, the number of transmissions required by FWR is arbitrarily better than that of existing approaches. Specifically, FWR requires O(n) messages on bounded-degree graphs with n nodes, whereas classical forwarding and an approach based on network coding both require ω(n) messages. Our results are obtained using combinatorial and probabilistic arguments. Notably, they do not depend on expansion properties of the underlying graph, and consequently the message complexity of FWR is arbitrarily better than classical forwarding even on constant-degree expander graphs, as n \rightarrow \infty. In resource-constrained applications, where each transmission consumes battery power and bandwidth, our results suggest that using a small amount of memory at each node leads to a significant savings.

cs.DC↗

arXiv2012

Growing a Network on a Given Substrate

Conventional studies of network growth models mainly look at the steady state degree distribution of the graph. Often long time behavior is considered, hence the initial condition is ignored. In this contribution, the time evolution of the degree distribution is the center of attention. We consider two specific growth models; incoming nodes with uniform and preferential attachment, and the degree distribution of the graph for arbitrary initial condition is obtained as a function of time. This allows us to characterize the transient behavior of the degree distribution, as well as to quantify the rate of convergence to the steady-state limit.

physics.soc-ph↗

arXiv2012

Background Subtraction for Online Calibration of Baseline RSS in RF Sensing Networks

Radio frequency (RF) sensing networks are a class of wireless sensor networks (WSNs) which use RF signals to accomplish tasks such as passive device-free localization and tracking. The algorithms used for these tasks usually require access to measurements of baseline received signal strength (RSS) on each link. However, it is often impossible to collect this calibration data (measurements collected during an offline calibration period when the region of interest is empty of targets). We propose adapting background subtraction methods from the field of computer vision to estimate baseline RSS values from measurements taken while the system is online and obstructions may be present. This is done by forming an analogy between the intensity of a background pixel in an image and the baseline RSS value of a WSN link and then translating the concepts of temporal similarity, spatial similarity and spatial ergodicity which underlie specific background subtraction algorithms to WSNs. Using experimental data, we show that these techniques are capable of estimating baseline RSS values with enough accuracy that RF tomographic tracking can be carried out in a variety of different environments without the need for a calibration period.

cs.NI↗

arXiv2011

GSGS: A Computational Framework to Reconstruct Signaling Pathways from Gene Sets

We propose a novel two-stage Gene Set Gibbs Sampling (GSGS) framework, to reverse engineer signaling pathways from gene sets inferred from molecular profiling data. We hypothesize that signaling pathways are structurally an ensemble of overlapping linear signal transduction events which we encode as Information Flow Gene Sets (IFGS's). We infer pathways from gene sets corresponding to these events subjected to a random permutation of genes within each set. In Stage I, we use a source separation algorithm to derive unordered and overlapping IFGS's from molecular profiling data, allowing cross talk among IFGS's. In Stage II, we develop a Gibbs sampling like algorithm, Gene Set Gibbs Sampler, to reconstruct signaling pathways from the latent IFGS's derived in Stage I. The novelty of this framework lies in the seamless integration of the two stages and the hypothesis of IFGS's as the basic building blocks for signal pathways. In the proof-of-concept studies, our approach is shown to outperform the existing Bayesian network approaches using both continuous and discrete data generated from benchmark networks in the DREAM initiative. We perform a comprehensive sensitivity analysis to assess the robustness of the approach. Finally, we implement the GSGS framework to reconstruct signaling pathways in breast cancer cells.

q-bio.QM↗

arXiv2011

GANC: Greedy Agglomerative Normalized Cut

This paper describes a graph clustering algorithm that aims to minimize the normalized cut criterion and has a model order selection procedure. The performance of the proposed algorithm is comparable to spectral approaches in terms of minimizing normalized cut. However, unlike spectral approaches, the proposed algorithm scales to graphs with millions of nodes and edges. The algorithm consists of three components that are processed sequentially: a greedy agglomerative hierarchical clustering procedure, model order selection, and a local refinement. For a graph of n nodes and O(n) edges, the computational complexity of the algorithm is O(n log^2 n), a major improvement over the O(n^3) complexity of spectral methods. Experiments are performed on real and synthetic networks to demonstrate the scalability of the proposed approach, the effectiveness of the model order selection procedure, and the performance of the proposed algorithm in terms of minimizing the normalized cut metric.

cs.AI↗

arXiv2010

Real-Time Multi-path Tracking of Probabilistic Available Bandwidth

Applications such as traffic engineering and network provisioning can greatly benefit from knowing, in real time, what is the largest input rate at which it is possible to transmit on a given path without causing congestion. We consider a probabilistic formulation for available bandwidth where the user specifies the probability of achieving an output rate almost as large as the input rate. We are interested in estimating and tracking the network-wide probabilistic available bandwidth (PAB) on multiple paths simultaneously with minimal overhead on the network. We propose a novel framework based on chirps, Bayesian inference, belief propagation and active sampling to estimate the PAB. We also consider the time evolution of the PAB by forming a dynamic model and designing a tracking algorithm based on particle filters. We implement our method in a lightweight and practical tool that has been deployed on the PlanetLab network to do online experiments. We show through these experiments and simulations that our approach outperforms block-based algorithms in terms of input rate cost and probability of successful transmission.

cs.NI↗

arXiv2010

Large scale probabilistic available bandwidth estimation

The common utilization-based definition of available bandwidth and many of the existing tools to estimate it suffer from several important weaknesses: i) most tools report a point estimate of average available bandwidth over a measurement interval and do not provide a confidence interval; ii) the commonly adopted models used to relate the available bandwidth metric to the measured data are invalid in almost all practical scenarios; iii) existing tools do not scale well and are not suited to the task of multi-path estimation in large-scale networks; iv) almost all tools use ad-hoc techniques to address measurement noise; and v) tools do not provide enough flexibility in terms of accuracy, overhead, latency and reliability to adapt to the requirements of various applications. In this paper we propose a new definition for available bandwidth and a novel framework that addresses these issues. We define probabilistic available bandwidth (PAB) as the largest input rate at which we can send a traffic flow along a path while achieving, with specified probability, an output rate that is almost as large as the input rate. PAB is expressed directly in terms of the measurable output rate and includes adjustable parameters that allow the user to adapt to different application requirements. Our probabilistic framework to estimate network-wide probabilistic available bandwidth is based on packet trains, Bayesian inference, factor graphs and active sampling. We deploy our tool on the PlanetLab network and our results show that we can obtain accurate estimates with a much smaller measurement overhead compared to existing approaches.

cs.NI↗

arXiv2010

Multi-path Probabilistic Available Bandwidth Estimation through Bayesian Active Learning

Knowing the largest rate at which data can be sent on an end-to-end path such that the egress rate is equal to the ingress rate with high probability can be very practical when choosing transmission rates in video streaming or selecting peers in peer-to-peer applications. We introduce probabilistic available bandwidth, which is defined in terms of ingress rates and egress rates of traffic on a path, rather than in terms of capacity and utilization of the constituent links of the path like the standard available bandwidth metric. In this paper, we describe a distributed algorithm, based on a probabilistic graphical model and Bayesian active learning, for simultaneously estimating the probabilistic available bandwidth of multiple paths through a network. Our procedure exploits the fact that each packet train provides information not only about the path it traverses, but also about any path that shares a link with the monitored path. Simulations and PlanetLab experiments indicate that this process can dramatically reduce the number of probes required to generate accurate estimates.

cs.NI↗