Graph Contrastive Learning (GCL) has proven effective in mitigating data sparsity and enhancing representation learning for recommendation. Yet, most GCL frameworks indiscriminately treat all non-anchor nodes as negatives during contrastive sampling, often leading to the false negative problem where semantically similar nodes are incorrectly repelled. Previous attempts to mitigate this issue rely on predetermined heuristics or local neighborhood mining, which struggle to reliably identify false negatives. More critically, they often overlook authentic user-item interactions for anchoring sample relationships. As a result, this paper presents MACRec, a Multi-View subspace-Alignment framework designed to Calibrate contrastive sampling in GCLbased Recommendation. MACRec comprises three core components: (1) a Multi-View Affinity (MVA) module that captures consistent semantic relations across multiple augmentations via self-expression modeling; (2) a Cross-Subspace Alignment (CSA) mechanism that leverages authentic useritem behavioral interactions to enforce semantic consistency across user and item subspaces; and (3) a Calibrationbased Contrastive Reweighting (CCR) strategy to dynamically down-weight potential false negatives during the contrastive learning process. Extensive experiments on three realworld benchmarks demonstrate that MACRec consistently improves performance across various augmentation backbones, achieving up to 14.55% relative gains.

Graph Contrastive Learning (GCL) emerges as a powerful approach in recommendation systems, leveraging graph structures to learn effective representations. However, existing contrastive sampling strategies often introduce unintended biases, most notably, the misclassification of genuine positive samples as negatives, which undermines representation quality and overall recommendation performance. Accordingly, this paper revisits the conventional contrastive sampling and introduces Negative-Free Sampling for Graph Contrastive Learning (NFS). NFS adopts a two-stage sampling strategy that selectively identifies and utilizes only positive instances during training. By removing reliance on negative samples, it effectively mitigates misclassification bias and improves the semantic alignment between related representations. In addition, a comprehensive theoretical analysis is also provided to establish the robustness of NFS against representation collapse. Experimental results on three benchmarks demonstrate that NFS consistently outperforms or performs state-of-the-art methods, achieving up to a 14.2% relative improvement across evaluated datasets. In addition, a detailed ablation study is also provided to examine how exclusively leveraging positive samples contributes to the efficiency of GCL. The results further demonstrate the plug-and-play nature of the proposed method and its resilience to noisy data.

Fourteen years after the invention of Bitcoin, there has been a proliferation of many permissionless blockchains. Each such chain provides a public ledger that can be written to and read from by anyone. In this multi-chain world, a natural question arises: what is the optimal security an existing blockchain, a consumer chain, can extract by only reading and writing to k other existing blockchains, the provider chains? We design a protocol, called interchain timestamping, and show that it extracts the maximum economic security from the provider chains, as quantified by the slashable safety resilience. We observe that interchain timestamps are already provided by light-client based bridges, so interchain timestamping can be readily implemented for Cosmos chains connected by the Inter-Blockchain Communication (IBC) protocol. We compare interchain timestamping with cross-staking, the original solution to mesh security, as well as with Trustboost, another recent security sharing protocol.

Today's blockchain designs suffer from a trilemma claiming that no blockchain system can simultaneously achieve decentralization, security, and performance scalability. For current blockchain systems, as more nodes join the network, the efficiency of the system (computation, communication, and storage) stays constant at best. A leading idea for enabling blockchains to scale efficiency is the notion of sharding: different subsets of nodes handle different portions of the blockchain, thereby reducing the load for each individual node. However, existing sharding proposals achieve efficiency scaling by compromising on trust - corrupting the nodes in a given shard will lead to the permanent loss of the corresponding portion of data. In this paper, we settle the trilemma by demonstrating a new protocol for coded storage and computation in blockchains. In particular, we propose PolyShard: “polynomially coded sharding” scheme that achieves information-theoretic upper bounds on the efficiency of the storage, system throughput, as well as on trust, thus enabling a truly scalable system. We provide simulation results that numerically demonstrate the performance improvement over state of the arts, and the scalability of the PolyShard system. Finally, we discuss potential enhancements, and highlight practical considerations in building such a system.

We introduce Coded State Machine (CSM), an information-theoretic framework to securely and efficiently execute multiple state machines on Byzantine nodes. The standard method of solving this problem is using State Machine Replication, which achieves high security at the cost of low efficiency. CSM simultaneously achieves the optimal linear scaling in storage, throughput, and security with increasing network size. The storage is scaled via the design of Lagrange coded states and coded input commands that require the same storage size as their origins. The computational efficiency is scaled using a novel delegation algorithm, called INTERMIX, which is an information-theoretically verifiable matrix-vector multiplication algorithm of independent interest.

We study the interplay between the throughput and average packet decoding delay (APDD) of linear network coded (LNC) wireless broadcast systems through studying the approximation of throughput and APDD. We first define strong and weak approximations (based on whether the approximation holds for every receiver or not). We then prove that LNC techniques that strongly approximate throughput can also strongly approximate APDD, but those that weakly approximate throughput do not necessarily weakly approximate APDD. We prove that all throughput-optimal LNC techniques, including random linear network coding, strongly approximate APDD with a ratio between 4/3 and 2. We also prove that all memoryless LNC techniques, including instantly decodable network coding techniques, cannot strongly or weakly approximate throughput, nor strongly approximate APDD.

Distributed training of deep nets is an important technique to address some of the present day computing challenges like memory consumption and computational demands. Classical distributed approaches, synchronous or asynchronous, are based on the parameter server architecture, i.e., worker nodes compute gradients which are communicated to the parameter server while updated parameters are returned. Recently, distributed training with AllReduce operations gained popularity as well. While many of those operations seem appealing, little is reported about wall-clock training time improvements. In this paper, we carefully analyze the AllReduce based setup, propose timing models which include network latency, bandwidth, cluster size and compute time, and demonstrate that a pipelined training with a width of two combines the best of both synchronous and asynchronous training. Specifically, for a setup consisting of a four-node GPU cluster we show wall-clock time training improvements of up to 5.4x compared to conventional approaches.

Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation. To alleviate this problem, several scalar quantization techniques have been developed to compress the gradients. But these techniques could perform poorly when used together with decentralized aggregation protocols like ring all-reduce (RAR), mainly due to their inability to directly aggregate compressed gradients. In this paper, we empirically demonstrate the strong linear correlations between CNN gradients, and propose a gradient vector quantization technique, named GradiVeQ, to exploit these correlations through principal component analysis (PCA) for substantial gradient dimension reduction. GradiveQ enables direct aggregation of compressed gradients, hence allows us to build a distributed learning system that parallelizes GradiveQ gradient compression and RAR communications. Extensive experiments on popular CNNs demonstrate that applying GradiveQ slashes the wall-clock gradient aggregation time of the original RAR by more than 5x without noticeable accuracy loss, and reduce the end-to-end training time by almost 50%. The results also show that \GradiveQ is compatible with scalar quantization techniques such as QSGD (Quantized SGD), and achieves a much higher speed-up gain under the same compression ratio.

Deterministic linear network coding (DLNC) is an important family of network coding techniques for wireless packet broadcast. In this paper, we show that DLNC is strongly related to and can be effectively studied using matroid theory without bridging index coding. We prove the equivalence between the DLNC solution and matrix matroid. We use this equivalence to study the performance limits of DLNC in terms of the number of transmissions and its dependence on the finite field size. Specifically, we derive the sufficient and necessary condition for the existence of perfect DLNC solutions and prove that such solutions may not exist over certain finite fields. We then show that identifying perfect solutions over any finite field is still an open problem in general. To fill this gap, we develop a heuristic algorithm which employs graphic matroids to find perfect DLNC solutions over any finite field. Numerical results show that its performance in terms of minimum number of transmissions is close to the lower bound, and is better than random linear network coding when the field size is not so large.

Our primary goal in this paper is to better understand and extend the achievable tradeoffs between the throughput and decoding delay performance of network coded wireless broadcast. To this end, we traverse the performance gap between two linear network coding schemes: random linear network coding (RLNC) and instantly decodable network coding (IDNC). Our approach is to appropriately partition a block of partially received data packets into subgenerations and broadcast them separately using RLNC. Through analyzing the factors that affect the performance of a generic partitioning scheme, we are led to develop a coding framework in which subgenerations are created from IDNC coding sets in an IDNC solution. This coding framework consists of a series of coding schemes, with classic RLNC and IDNC identified as two extreme schemes. We develop two basic partitioning guidelines, including disjoint partitioning and even partitioning. We design various implementations of this coding framework, such as partitioning algorithms and generation scheduling strategies, to further improve its throughput and decoding delay, to manage feedback frequency and coding complexity, or to achieve in-block performance adaption. Their effectiveness is verified through extensive simulations, and their performance is compared with an existing work in the literature.

In this paper, a new network coding model is proposed to unify instantly decodable network coding (IDNC) and random linear network coding (RLNC), which have been considered to be incompatible in the literature. This model is based on a novel definition of generation, which is built upon optimal IDNC solutions. Under this model, IDNC and RLNC are only two extreme cases with specific generation sizes. Throughput and delay properties of this model, measured by block completion time and packet decoding delay, respectively, are studied, which fill the gap between IDNC and RLNC and thus provide a good understanding on the throughput-delay tradeoff of network coding. An efficient adaptive scheme is then designed, which allows in-block switch among IDNC and different levels of RLNC, so that the system's throughput and delay can be fine-tuned to meet the real-time requirements of the application. Extensive simulations are performed to demonstrate how the proposed generation size interacts with the number of receivers and the channel quality to affect the overall system performance.

In this paper we propose a novel timing and frequency synchronization and decoding method for the PI symbol in DVB-T2 based on the correlation between the received signal and the time domain PI symbols. This method does not require post-FFT decoding and is insensitive to the frequency-shift offset and continuous-wave (CW) interference. The performance of the proposed method is evaluated via computer simulations, which shows that not only does it achieve good synchronization performance, but also it provides a decoding SNR gain of at least 6dB in AWGN channel and at least 2dB in multipath Rayleigh fading channel compared with the performance reported in the standard guidelines.