arXiv subjects

Shenghao Yang

Publications and source records attributed to Shenghao Yang.

At least 37 records · Page 2Linked to original sources

arXiv2023

Collaborative Word-based Pre-trained Item Representation for Transferable Recommendation

Item representation learning (IRL) plays an essential role in recommender systems, especially for sequential recommendation. Traditional sequential recommendation models usually utilize ID embeddings to represent items, which are not shared across different domains and lack the transferable ability. Recent studies use pre-trained language models (PLM) for item text embeddings (text-based IRL) that are universally applicable across domains. However, the existing text-based IRL is unaware of the important collaborative filtering (CF) information. In this paper, we propose CoWPiRec, an approach of Collaborative Word-based Pre-trained item representation for Recommendation. To effectively incorporate CF information into text-based IRL, we convert the item-level interaction data to a word graph containing word-level collaborations. Subsequently, we design a novel pre-training task to align the word-level semantic- and CF-related item representation. Extensive experimental results on multiple public datasets demonstrate that compared to state-of-the-art transferable sequential recommenders, CoWPiRec achieves significantly better performances in both fine-tuning and zero-shot settings for cross-scenario recommendation and effectively alleviates the cold-start issue. The code is available at: https://github.com/ysh-1998/CoWPiRec.

cs.IR↗

arXiv2023

On Achievable Rates of Line Networks with Generalized Batched Network Coding

To better understand the wireless network design with a large number of hops, we investigate a line network formed by general discrete memoryless channels (DMCs), which may not be identical. Our focus lies on Generalized Batched Network Coding (GBNC) that encompasses most existing schemes as special cases and achieves the min-cut upper bounds as the parameters batch size and inner block length tend to infinity. The inner blocklength of GBNC provides upper bounds on the required latency and buffer size at intermediate network nodes. By employing a bottleneck status technique, we derive new upper bounds on the achievable rates of GBNCs These bounds surpass the min-cut bound for large network lengths when the inner blocklength and batch size are small. For line networks of canonical channels, certain upper bounds hold even with relaxed inner blocklength constraints. Additionally, we employ a channel reduction technique to generalize the existing achievability results for line networks with identical DMCs to networks with non-identical DMCs. For line networks with packet erasure channels, we make refinement in both the upper bound and the coding scheme, and showcase their proximity through numerical evaluations.

cs.IT↗

arXiv2023

Wireless Network Scheduling with Discrete Propagation Delays: Theorems and Algorithms

This paper focuses on the link scheduling problem in networks where signal delays between nodes are multiples of a time interval. To model such networks, a directed hypergraph is employed, along with an integer matrix that specifies the delays. The link scheduling problem is closely connected to the independent sets of the periodic hypergraph induced by the network model. However, due to the infinite number of vertices, it is impractical to enumerate the independent sets of the periodic hypergraph using generic graph algorithms. To tackle this challenge, a graphical approach is proposed in this paper. The link scheduling rate region is characterized using a finite directed graph called a scheduling graph, which is derived from the network model. A collision-free schedule of the network corresponds to a path in the scheduling graph, and the rate region is determined by the convex hull of the rate vectors associated with the cycles in the scheduling graph. Although existing cycle enumeration algorithms can be employed to calculate the rate region, their computational complexity becomes prohibitively high as the size of the scheduling graph grows exponentially with the number of network links. To address this issue, the dominance property of a special scheduling graph called the step-T scheduling graph is investigated. This property allows the utilization of specific subgraphs of the step-T scheduling graph to characterize the scheduling rate region, achieving a reduction in both the number of cycles and their lengths. For common problems such as calculating the rate region and maximizing a weighted sum of the scheduling rates, algorithms leveraging the dominance property are developed. These algorithms can be more efficient than using generic graph algorithms directly on the scheduling graphs.

cs.IT↗

arXiv2023

On Optimal Finite-length Block Codes of Size Four for Binary Symmetric Channels

A binary code of blocklength $n$ and codebook size $M$ is called an $(n,M)$ code, which is studied for memoryless binary symmetric channels (BSCs) with the maximum likelihood (ML) decoding. For any $n \geq 2$, some optimal codes among the linear $(n,4)$ codes have been explicitly characterized in the previous study, but whether the optimal codes among the linear codes are better than all the nonlinear codes or not is unknown. In this paper, we first show that for any $n\geq 2$, there exists an optimal code (among all the $(n,4)$ codes) that is either linear or in a subset of nonlinear codes, called Class-I codes. We identified all the optimal codes among the linear $(n,4)$ codes for each blocklength $n\geq 2$, and found ones that were not given in literature. For any $n$ from $2$ to $300$, all the optimal $(n,4)$ codes are identified, where except for $n=3$, all the optimal $(n,4)$ codes are equivalent to linear codes. There exist optimal $(3,4)$ codes that are not equivalent to linear codes. Furthermore, we derive a subset of nonlinear codes called Class-II codes and justify that for any $n >300$, the set composed of linear, Class-I and Class-II codes and their equivalent codes contains all the optimal $(n,4)$ codes. Both Class-I and Class-II codes are close to linear codes in the sense that they involve only one type of columns that are not included in linear codes. Our results are obtained using a new technique to compare the ML decoding performance of two codes, featured by a partition of the entire range of the channel output.

cs.IT↗

arXiv2023

Weighted Flow Diffusion for Local Graph Clustering with Node Attributes: an Algorithm and Statistical Guarantees

Local graph clustering methods aim to detect small clusters in very large graphs without the need to process the whole graph. They are fundamental and scalable tools for a wide range of tasks such as local community detection, node ranking and node embedding. While prior work on local graph clustering mainly focuses on graphs without node attributes, modern real-world graph datasets typically come with node attributes that provide valuable additional information. We present a simple local graph clustering algorithm for graphs with node attributes, based on the idea of diffusing mass locally in the graph while accounting for both structural and attribute proximities. Using high-dimensional concentration results, we provide statistical guarantees on the performance of the algorithm for the recovery of a target cluster with a single seed node. We give conditions under which a target cluster generated from a fairly general contextual random graph model, which includes both the stochastic block model and the planted cluster model as special cases, can be fully recovered with bounded false positives. Empirically, we validate all theoretical claims using synthetic data, and we show that incorporating node attributes leads to superior local clustering performances using real-world graph datasets.

cs.SI↗

arXiv2023

Graph Attention Retrospective

Graph-based learning is a rapidly growing sub-field of machine learning with applications in social networks, citation networks, and bioinformatics. One of the most popular models is graph attention networks. They were introduced to allow a node to aggregate information from features of neighbor nodes in a non-uniform way, in contrast to simple graph convolution which does not distinguish the neighbors of a node. In this paper, we theoretically study the behaviour of graph attention networks. We prove multiple results on the performance of the graph attention mechanism for the problem of node classification for a contextual stochastic block model. Here, the node features are obtained from a mixture of Gaussians and the edges from a stochastic block model. We show that in an "easy" regime, where the distance between the means of the Gaussians is large enough, graph attention is able to distinguish inter-class from intra-class edges. Thus it maintains the weights of important edges and significantly reduces the weights of unimportant edges. Consequently, we show that this implies perfect node classification. In the "hard" regime, we show that every attention mechanism fails to distinguish intra-class from inter-class edges. In addition, we show that graph attention convolution cannot (almost) perfectly classify the nodes even if intra-class edges could be separated from inter-class edges. Beyond perfect node classification, we provide a positive result on graph attention's robustness against structural noise in the graph. In particular, our robustness result implies that graph attention can be strictly better than both the simple graph convolution and the best linear classifier of node features. We evaluate our theoretical results on synthetic and real-world data.

cs.LG↗

arXiv2023

Reliable Throughput of Generalized Collision Channel without Synchronization

We consider a generalized collision channel model for general multi-user communication systems, an extension of Massey and Mathys' collision channel without feedback for multiple access communications. In our model, there are multiple transmitters and receivers sharing the same communication channel. The transmitters are not synchronized and arbitrary time offsets between transmitters and receivers are assumed. A ``collision" occurs if two or more packets from different transmitters partially or completely overlap at a receiver. Our model includes the original collision channel as a special case. This paper focuses on reliable throughputs that are approachable for arbitrary time offsets. We consider both slot-synchronized and non-synchronized cases and characterize their reliable throughput regions for the generalized collision channel model. These two regions are proven to coincide. Moreover, it is shown that the protocol sequences constructed for multiple access communication remain ``throughput optimal" in the generalized collision channel model. We also identify the protocol sequences that can approach the outer boundary of the reliable throughput region.

cs.IT↗

arXiv2023

Equivariant Hypergraph Diffusion Neural Operators

Hypergraph neural networks (HNNs) using neural networks to encode hypergraphs provide a promising way to model higher-order relations in data and further solve relevant prediction tasks built upon such higher-order relations. However, higher-order relations in practice contain complex patterns and are often highly irregular. So, it is often challenging to design an HNN that suffices to express those relations while keeping computational efficiency. Inspired by hypergraph diffusion algorithms, this work proposes a new HNN architecture named ED-HNN, which provably represents any continuous equivariant hypergraph diffusion operators that can model a wide range of higher-order relations. ED-HNN can be implemented efficiently by combining star expansions of hypergraphs with standard message passing neural networks. ED-HNN further shows great superiority in processing heterophilic hypergraphs and constructing deep models. We evaluate ED-HNN for node classification on nine real-world hypergraph datasets. ED-HNN uniformly outperforms the best baselines over these nine datasets and achieves more than 2\%$\uparrow$ in prediction accuracy over four datasets therein.

cs.LG↗

arXiv2022

On Classification Thresholds for Graph Attention with Edge Features

The recent years we have seen the rise of graph neural networks for prediction tasks on graphs. One of the dominant architectures is graph attention due to its ability to make predictions using weighted edge features and not only node features. In this paper we analyze, theoretically and empirically, graph attention networks and their ability of correctly labelling nodes in a classic classification task. More specifically, we study the performance of graph attention on the classic contextual stochastic block model (CSBM). In CSBM the nodes and edge features are obtained from a mixture of Gaussians and the edges from a stochastic block model. We consider a general graph attention mechanism that takes random edge features as input to determine the attention coefficients. We study two cases, in the first one, when the edge features are noisy, we prove that the majority of the attention coefficients are up to a constant uniform. This allows us to prove that graph attention with edge features is not better than simple graph convolution for achieving perfect node classification. Second, we prove that when the edge features are clean graph attention can distinguish intra- from inter-edges and this makes graph attention better than classic graph convolution.

cs.LG↗

arXiv2021

Repeated-root Constacyclic Codes with Optimal Locality

A code is called a locally repairable code (LRC) if any code symbol is a function of a small fraction of other code symbols. When a locally repairable code is employed in a distributed storage systems, an erased symbol can be recovered by accessing only a small number of other symbols, and hence alleviating the network resources required during the repair process. In this paper we consider repeated-root constacyclic codes, which is a generalization of cyclic codes, that are optimal with respect to a Singleton-like bound on minimum distance. An LRC with the structure of a constacyclic code can be encoded efficiently using any encoding algorithm for constacyclic codes in general. In this paper we obtain optimal LRCs among these repeated-root constacyclic codes. Several infinite classes of optimal LRCs over a fixed alphabet are found. Under a further assumption that the ambient space of the repeated-root constacyclic codes is a chain ring, we show that there is no other optimal LRC.

cs.IT↗

arXiv2021

Utility Maximization for Multihop Wireless Networks Employing BATS Codes

BATS (BATched Sparse) codes are a class of efficient random linear network coding variation that has been studied for multihop wireless networks mostly in scenarios of a single communication flow. Towards sophisticated multi-flow network communications, we formulate a network utility maximization (NUM) problem that jointly optimizes the BATS code parameters of all the flows and network scheduling. The NUM problem adopts a batch-wise packet loss model that can be obtained from the network local statistics without any constraints on packet loss patterns. Moreover, the NUM problem allows a different number of recoded packets to be transmitted for different batches in a flow, which is called adaptive recoding. Due to both the probably nonconcave objective and the BATS code-related variables, the algorithms developed for the existing flow optimization problems cannot be applied directly to solve our NUM problem. We introduce a two-step algorithm to solve our NUM problem, where the first step solves the problem with nonadaptive recoding schemes, and the second step optimizes adaptive recoding hop-by-hop from upstream to downstream in each flow. We perform various numerical evaluations and simulations to verify the effectiveness and efficiency of the algorithm.

cs.IT↗

arXiv2021

Intrablock Interleaving for Batched Network Coding with Blockwise Adaptive Recoding

Batched network coding (BNC) is a low-complexity solution to network transmission in multi-hop packet networks with packet loss. BNC encodes the source data into batches of packets. As a network coding scheme, the intermediate nodes perform recoding on the received packets belonging to the same batch instead of just forwarding them. A recoding scheme that may generate more recoded packets for batches of a higher rank is also called adaptive recoding. Meanwhile, in order to combat burst packet loss, the transmission of a block of batches can be interleaved. Stream interleaving studied in literature achieves the maximum separation among any two consecutive packets of a batch, but permutes packets across blocks and hence cannot bound the buffer size and the latency. To resolve the issue of stream interleaver, we design an intrablock interleaver for adaptive recoding that can preserve the advantages of using a block interleaver when the number of recoded packets is the same for all batches. We use potential energy in classical mechanics to measure the performance of an interleaver, and propose an algorithm to optimize the interleaver with this performance measure. Our problem formulation and algorithm for intrablock interleaving are also of independent interest.

cs.IT↗

arXiv2021

A Unified Adaptive Recoding Framework for Batched Network Coding

Batched network coding is a variation of random linear network coding which has low computational and storage costs. In order to adapt to random fluctuations in the number of erasures in individual batches, it is not optimal to recode and transmit the same number of packets for all batches. Different distributed optimization models, which are called adaptive recoding schemes, were formulated for this purpose. The key component of these optimization problems is the expected value of the rank distribution of a batch at the next network node, which is also known as the expected rank. In this paper, we put forth a unified adaptive recoding framework with an arbitrary recoding field size. We show that the expected rank functions are concave when the packet loss pattern is a stationary stochastic process, which covers but not limited to independent packet loss and Gilbert-Elliott packet loss model. Under this concavity assumption, we show that there always exists a solution which not only can minimize the randomness on the number of recoded packets but also can tolerate rank distribution errors due to inaccurate measurements or limited precision of the machine. We provide an algorithm to obtain such an optimal optimal solution, and propose tuning schemes that can turn any feasible solution into a desired optimal solution.

cs.IT↗

arXiv2021

Targeted Pandemic Containment Through Identifying Local Contact Network Bottlenecks

Decision-making about pandemic mitigation often relies upon simulation modelling. Models of disease transmission through networks of contacts--between individuals or between population centres--are increasingly used for these purposes. Real-world contact networks are rich in structural features that influence infection transmission, such as tightly-knit local communities that are weakly connected to one another. In this paper, we propose a new flow-based edge-betweenness centrality method for detecting bottleneck edges that connect nodes in contact networks. In particular, we utilize convex optimization formulations based on the idea of diffusion with p-norm network flow. Using simulation models of COVID-19 transmission through real network data at both individual and county levels, we demonstrate that targeting bottleneck edges identified by the proposed method reduces the number of infected cases by up to 10% more than state-of-the-art edge-betweenness methods. Furthermore, the proposed method is orders of magnitude faster than existing methods.

cs.SI↗

arXiv2021

Small-Sample Inferred Adaptive Recoding for Batched Network Coding

Batched network coding is a low-complexity network coding solution to feedbackless multi-hop wireless packet network transmission with packet loss. The data to be transmitted is encoded into batches where each of which consists of a few coded packets. Unlike the traditional forwarding strategy, the intermediate network nodes have to perform recoding, which generates recoded packets by network coding operations restricted within the same batch. Adaptive recoding is a technique to adapt the fluctuation of packet loss by optimizing the number of recoded packets per batch to enhance the throughput. The input rank distribution, which is a piece of information regarding the batches arriving at the node, is required to apply adaptive recoding. However, this distribution is not known in advance in practice as the incoming link's channel condition may change from time to time. On the other hand, to fully utilize the potential of adaptive recoding, we need to have a good estimation of this distribution. In other words, we need to guess this distribution from a few samples so that we can apply adaptive recoding as soon as possible. In this paper, we propose a distributionally robust optimization for adaptive recoding with a small-sample inferred prediction of the input rank distribution. We develop an algorithm to efficiently solve this optimization with the support of theoretical guarantees that our optimization's performance would constitute as a confidence lower bound of the optimal throughput with high probability.

cs.IT↗

arXiv2021

Local Hyper-Flow Diffusion

Recently, hypergraphs have attracted a lot of attention due to their ability to capture complex relations among entities. The insurgence of hypergraphs has resulted in data of increasing size and complexity that exhibit interesting small-scale and local structure, e.g., small-scale communities and localized node-ranking around a given set of seed nodes. Popular and principled ways to capture the local structure are the local hypergraph clustering problem and related seed set expansion problem. In this work, we propose the first local diffusion method that achieves edge-size-independent Cheeger-type guarantee for the problem of local hypergraph clustering while applying to a rich class of higher-order relations that covers many previously studied special cases. Our method is based on a primal-dual optimization formulation where the primal problem has a natural network flow interpretation, and the dual problem has a cut-based interpretation using the $\ell_2$-norm penalty on associated cut-costs. We demonstrate the new technique is significantly better than state-of-the-art methods on both synthetic and real-world data.

cs.LG↗

arXiv2021

BAR: Blockwise Adaptive Recoding for Batched Network Coding

Multi-hop networks become popular network topologies in various emerging Internet of things applications. Batched network coding (BNC) is a solution to reliable communications in such networks with packet loss. By grouping packets into small batches and restricting recoding to the packets belonging to the same batch, BNC has a much smaller computational and storage requirements at the intermediate nodes compared with a direct application of random linear network coding. In this paper, we propose a practical recoding scheme called blockwise adaptive recoding (BAR) which learns the latest channel knowledge from short observations so that BAR can adapt to the fluctuation of channel conditions. We focus on investigating practical concerns such as the design of efficient BAR algorithms. We also design and investigate feedback schemes for BAR under imperfect feedback systems. Our numerical evaluations show that BAR has significant throughput gain for small batch size compared with the existing baseline recoding scheme. More importantly, this gain is insensitive to inaccurate channel knowledge. This encouraging result suggests that BAR is suitable to be realized in practice as the exact channel model and its parameters could be unknown and subject to change from time to time.

cs.IT↗

arXiv2020

$p$-Norm Flow Diffusion for Local Graph Clustering

Local graph clustering and the closely related seed set expansion problem are primitives on graphs that are central to a wide range of analytic and learning tasks such as local clustering, community detection, nodes ranking and feature inference. Prior work on local graph clustering mostly falls into two categories with numerical and combinatorial roots respectively. In this work, we draw inspiration from both fields and propose a family of convex optimization formulations based on the idea of diffusion with p-norm network flow for $p\in (1,\infty)$. In the context of local clustering, we characterize the optimal solutions for these optimization problems and show their usefulness in finding low conductance cuts around input seed set. In particular, we achieve quadratic approximation of conductance in the case of $p=2$ similar to the Cheeger-type bounds of spectral methods, constant factor approximation when $p\rightarrow\infty$ similar to max-flow based methods, and a smooth transition for general $p$ values in between. Thus, our optimization formulation can be viewed as bridging the numerical and combinatorial approaches, and we can achieve the best of both worlds in terms of speed and noise robustness. We show that the proposed problem can be solved in strongly local running time for $p\ge 2$ and conduct empirical evaluations on both synthetic and real-world graphs to illustrate our approach compares favorably with existing methods.

cs.LG↗