Recent research aims to improve cross-lingual transfer learning in low-resource scenarios by optimizing the internal representations of multilingual models. However, previous methods typically rely on large-scale parallel corpora and overlook the subtle semantic differences between languages, leading to excessive clustering or collapse of local semantic units in the embedding space. This weakens the model's generalization ability on unseen data and its robustness under noisy conditions. To address this, we propose XLingLearn, a collaborative optimization framework that enhances cross-lingual transfer by expanding robust embedding regions and refining multilingual embedding space. Specifically, we design a distance-dispersion constraint strategy to push overly clustered semantic units apart to prevent semantic collapse, and introduce a direction-consistency constraint to prevent semantic bias. Additionally, we introduce an attention consistency module to stabilize the robust region. Finally, to mitigate the embedding space and context space mismatch caused by data augmentation, we introduce a debiasing-optimization regularization term, which enhances transfer efficiency and stability. Experimental results show that XLingLearn improves cross-lingual transfer performance across 17 target languages in the XNLI and PAWS-X tasks, enhancing generalization and robustness under low-resource and non-parallel conditions.

In this paper, we consider distributed testing problems with cascaded encoders, which allow cascaded communications among encoders so that each encoder can utilize messages from other encoders for encoding. We first focus on a special case of testing against independence and design a scheme that enables each encoder to take advantage of extra information from other encoders. We also derive a matching upper bound and prove that the designed scheme is optimal. We then investigate the case with general hypotheses and obtain a lower bound on the type 2 error exponent. We further compare the performances that can be achieved by schemes with and without cascaded communications. We show that cascaded communication improves the performance in terms of the type 2 error exponent under positive rate communication constraints. On the other hand, we prove that cascaded communication does not provide performance gain under zero-rate communication constraints.

In this paper, we consider the identity testing problems in the distributed setting, in which each terminal has data only relates to one random variable. Each terminal sends zero-rate message to the decision maker, and the decision maker decides the distribution of (Xn, Yn), which is indirectly revealed from the encoded messages, is the same as or λ-far from a given distribution. Interpreting this as a distributed composite hypothesis testing problem, we characterize the best error exponent of the type 2 error probability using a universal coding scheme under the exponential-type constraint on the type 1 error probability.

Motivated by distributed inference over big datasets problems, we study multi-terminal distributed hypothesis testing problems in which each terminal has data related to only one random variable. We consider a case of practical interest in which each terminal is allowed to send zero-rate messages to a decision maker. Subject to a constraint that the error exponent of the type 1 error probability is larger than a certain level, we characterize the best error exponent of the type 2 error probability using basic properties of the r-divergent sequences.

We propose a novel dynamic transparent virtual network embedding (VNE) algorithm, which considers node mapping and link mapping jointly, for network virtualization over optical orthogonal frequency-division multiplexing (O-OFDM) based elastic optical infrastructures. For each virtual optical network (VON) request, the algorithm first transfers the substrate optical network into a layered-auxiliary-graph according to the spectrum usage of each fiber link, then applies a node mapping approach that considers the local information of all substrate nodes, and accomplishes the link mapping, in a single layer of the auxiliary graph. The simulation results verify that the proposed algorithm considers the uniqueness of O-OFDM networks and outperforms two reference algorithms that directly apply the VNE schemes developed for Layer 2/3 or WDM network virtualization, by providing lower VON blocking probability. The simulations with a realistic topology also demonstrate that the average lengths of embedded substrate paths are well-controlled within the typical transmission reaches of O-OFDM signals. To the best of our knowledge, this is the first proposal that includes both link mapping and node mapping to address dynamic transparent VNE over elastic optical infrastructures.