Neural algorithmic reasoning has recently emerged as a popular research direction. It aims to train neural networks to mimic the step-by-step behavior of classical rule-based algorithms. More specifically, the execution of such algorithms can be abstracted as a sequence of states, where each state represents the intermediate outcome after an execution step. The training objective is to generate state sequences that replicate the underlying algorithmic process. A common framework for this task adopts an ``encoder-processor-decoder'' architecture, where the encoder learns representations of states, the processor simulates algorithmic steps, and the decoder reconstructs output states. While prior work has primarily focused on improving the processor, the role of the encoder in representation learning has received little attention. Most existing methods rely on simple MLP encoders, raising the question of whether such representations are sufficiently informative for supporting algorithmic reasoning. This paper investigates how to improve encoder representations for neural algorithmic reasoning. We propose a reconstruction module that aims to recover the input state from its encoded representation. This auxiliary reconstruction task encourages the encoder to retain critical information about the input. We demonstrate that incorporating this task during training improves the performance of existing neural architectures on standard benchmarks. Furthermore, we observe that current encoders often underutilize the correlations among features within a state. To address this, we draw inspiration from self-supervised learning and design an enhanced variant of the auxiliary task that encourages the encoder to capture intra-state feature dependencies. Experimental results show that our method enables the encoder to learn richer representations, thereby enhancing the performance of existing processors on algorithmic reasoning tasks.

Abstract Safe controller synthesis with formal guarantees is widely employed in safety-critical systems. However, existing controller synthesis methods are subject to significant limitations in scalability and efficiency. This paper presents a novel controller incremental synthesis framework guided by barrier certificates (BCs), thereby generating a safe controller with BC verification. To enhance verification efficiency, we construct a learning-enabled polynomial BC combined with efficient post-verification, which is transformed into smaller-scale linear Programming (LP) subproblems for feasibility determination. Furthermore, we have implemented a tool called ISafeC and evaluated its performance over a set of benchmark examples. The comparative experimental results demonstrate the effectiveness and efficiency of our approach.

In various domains such as transportation, resource management, and weather forecasting, there is an urgent need for methods that can provide predictions over a sufficiently long time horizon to encompass the period required for decision-making and implementation. Compared to traditional time series forecasting, ultra-long time series forecasting requires enhancing the model's ability to infer long time series, while maintaining inference costs within an acceptable range. To address this challenge, we propose the Boundary-Aware Periodicity-based sparsification strategy for Ultra-Long time series forecasting (BAP-UL).This method effectively captures periodic features in time series and reorganizes inputs and outputs into shorter sub-sequences for improved prediction accuracy. In the paper, we investigate several commonly used benchmark datasets and demonstrate that the proposed method can yield comparable performance across them.

Neural algorithmic reasoning is an emerging area of machine learning that focuses on building neural networks capable of solving complex algorithmic tasks. Recent advancements predominantly follow the standard supervised learning paradigm -- feeding an individual problem instance into the network each time and training it to approximate the execution steps of a classical algorithm. We challenge this mode and propose a novel open-book learning framework. In this framework, whether during training or testing, the network can access and utilize all instances in the training dataset when reasoning for a given instance. Empirical evaluation is conducted on the challenging CLRS Algorithmic Reasoning Benchmark, which consists of 30 diverse algorithmic tasks. Our open-book learning framework exhibits a significant enhancement in neural reasoning capabilities. Further, we notice that there is recent literature suggesting that multi-task training on CLRS can improve the reasoning accuracy of certain tasks, implying intrinsic connections between different algorithmic tasks. We delve into this direction via the open-book framework. When the network reasons for a specific task, we enable it to aggregate information from training instances of other tasks in an attention-based manner. We show that this open-book attention mechanism offers insights into the inherent relationships among various tasks in the benchmark and provides a robust tool for interpretable multi-task training.

Abstract There is a pressing need for learning controllers to endow systems with properties of safety and goal-reaching, which are crucial for many safety-critical systems. Reinforcement learning (RL) has been deployed successfully to synthesize controllers from user-defined reward functions encoding desired system requirements. However, it remains a significant challenge in synthesizing provably correct controllers with safety and goal-reaching requirements. To address this issue, we try to design a special hybrid polynomial-DNN controller which is easy to verify without losing its expressiveness and flexibility. This paper proposes a novel method to synthesize such a hybrid controller based on RL, low-degree polynomial fitting and knowledge distillation. It also gives a computational approach, by building and solving a constrained optimization problem coming from verification conditions to produce barrier certificates and Lyapunov-like functions, which can guarantee every trajectory from the initial set of the system with the resulted controller satisfies the given safety and goal-reaching requirements. We evaluate the proposed hybrid controller synthesis method on a set of benchmark examples, including several high-dimensional systems. The results validate the effectiveness and applicability of our approach.

Location-based recommendation has become a significant method to help people locate fascinating and appealing points of interest (POIs) with the rapid popularity of smart mobile devices and the prevalence of location-based social networks (LBSN). However, the sparsity of the user-POI matrix and the cold-start issue have generated serious challenges, resulting in a substantial decrease in collaborative filtering methods’ recommendation results. In reality, location-based recommendation demands spatiotemporal context awareness. In order to overcome these challenges, we develop an embedding model based on the heterogeneous graph attention network. Geographic influence, social relation and historical check-in influence are captured in a unified way by constructing a user-POI heterogeneous graph. Subsequently, we use the LSTM-based model to learn the category weight of the next POI to select. We are developing a score function to recommend the next POI for users by integrating category weights, user preferences and time impact. We conduct experiments on existing large-scale datasets to evaluate the performance of our model. The results demonstrate our proposal is superior to other rivals. Additionally, our method has been significantly improved compared with other competitive approaches in terms of recommending cold-start POI.

Unsupervised image-to-image translation is to learn a mapping function from one image domain to another with unpaired samples, which is an important task of computer vision. However, current unsupervised image-to-image translation methods only perform well on certain datasets. To handle the limitation, this paper proposes a novel framework termed as CSAGAN which contains a new discriminator structure, a novel attention module, and a new normalized function. The discriminator is an attention-guided feature pyramid discriminator which makes use of low-level and high-level features to determine an image’s realness. The new attention module integrating channel attention and spatial attention can guide generators focus on the most discriminative regions of feature maps to generate high-quality translated images. Moreover, our attention module embedded into generators requires less computation compared with other self-attention methods. In addition, the new normalized function helps generators limberly control the variation of shape, color, and texture through learning parameters. Experimental results indicate that our approach performs better than the current state-of-the-art methods.

Barrier certificates generation is widely used in verifying safety properties of hybrid systems because of the relatively low computational complexity it costs. Under sum of squares (SOS) relaxation, the problem of barrier certificate generation is equivalent to that of solving a bilinear matrix inequality (BMI) with a particular type. The paper reveals the special feature of the problem, and adopts it to build a novel computational method. The proposed method introduces a sequential iterative scheme that is able to find analytical solutions, rather than the nonlinear solving procedure to produce numerical solutions used by general BMI solvers and thus is more efficient than them. In addition, different from popular LMI solving based methods, it does not make the verification conditions more conservative, and thus reduces the risk of missing feasible solutions. Benefitting from these two appealing features, it can produce barrier certificates not amenable to existing methods, which is supported by a complexity analysis as well as the experiment on some benchmarks.

As a supervised learning method, Factorization Machine (FM) is famous for its capability of modeling feature interactions. However, FM's performance might be bad if we assign the same weight to all feature interactions, as not all of them are equally useful and productive. Attentional Factorization Machine (AFM) improves FM by discriminating the importance of distinctive feature interactions via a neural attention network. Nevertheless, the neural attention network in AFM is not fine-grained enough and it ignores the information of the fields implied by the features, which limits the performance of the model. In this work, we propose a novel model named IO-aware Factorization Machine (IOFM), which enhances the feature representation ability of attention mechanism in estimating weights via two awareness auxiliary matrices. To make the model more efficient, we further reduce the model parameters using canonical decomposition for the two auxiliary matrices and design a shared matrix to correlate the decomposed matrices. Extensive experiments on two real-world datasets indicate the superiority of our IOFM model over the state-of-the-art methods.

In this paper, we presented a formalization to the Clock Theory of He Jifeng in the Isabelle interactive theorem prover, we described the basic concepts of the theory in Isabelle and proved its soundness for programming hybrid systems.

In recent years, with the development of social networks, sentiment analysis has become one of the most important research topics in the field of natural language processing. The deep neural network model combining attention mechanism has achieved remarkable success in the task of target-based sentiment analysis. In current research, however, the attention mechanism is more combined with LSTM networks, such neural network- based architectures generally rely on complex computation and only focus on the single target, thus it is difficult to effectively distinguish the different polarities of variant targets in the same sentence. To address this problem, we propose a deep neural network model combining convolutional neural network and regional long short-term memory (CNN-RLSTM) for the task of target-based sentiment analysis. The approach can reduce the training time of neural network model through a regional LSTM. At the same time, the CNN-RLSTM uses a sentence-level CNN to extract sentiment features of the whole sentence, and controls the transmission of information through different weight matrices, which can effectively infer the sentiment polarities of different targets in the same sentence. Finally, experimental results on multi-domain datasets of two languages from SemEval2016 and auto data show that, our approach yields better performance than SVM and several other neural network models.

Reversible computing is so far the only way to circumvent the Landauer limit of CPU power efficiency, thus has attracted more and more attention recently due to its prospect in energy-efficient computing. To make reversible computing possible, much ground work needs to be studied, especially on reversible algorithms. We focus on designing reversible shortest path algorithms in this paper.

As a new computing paradigm, cloud computing has significantly contributed to the rapid development of massive data centers. However, the corresponding energy issue becomes increasingly challenging. In this paper, we focus on the energy saving issue for virtual machine (VM) selections on an overloaded host in a cloud computing environment. We analyze the energy influencing factors during a VM migration, then design energy efficient VM selection algorithms based on greedy algorithm and dynamic programming method. We conduct experiments with CloudSim and results show that the proposed algorithm in this paper can effectively reduce energy consumption while satisfying the SLA constraints.

VANET (Vehicular Ad hoc Network) is a special kind of ad hoc network in which each vehicle is regarded as a communication unit, which has attracted lots of attention in recent years. Vehicle's movement is restricted by road and environment in VANET, while traditional random mobility model and way-point mobility model can't reflect the realistic vehicle traces. How to evaluate wireless routing protocol in VANET based on real dynamic vehicle traces? In this paper, we have studied the communication methods between road traffic simulator SUMO(Simulation of Urban Mobility) and network simulator NS3. By establishing a feedback loop between them, we successfully build a coordination protocol to combine the traffic simulation power of SUMO and the network simulation capability of NS3. Finally, we present two scenarios to illustrate how our methods can simulate real VANET environment smoothly.

Routing protocols in Vehicular Ad hoc Network (VANET) have drawn lots of attention in recent years, most existing research efforts focus on designing IP-based protocols. In this paper, we present a new routing protocol for VANET based on Named Data Network (NDN). We optimize the routing path by using a new distance metric in the protocol, avoiding the shortcomings of hop-count based metric. Moreover, we use incremental broadcast and adaptive broadcast strategy according to vehicle density. In the experiment part, we construct a virtual urban scenario V-City to generate real world traffic and establish a coordinative test bed integrating SUMO with NS3. Simulation result shows that our protocol is more suitable for VANET environment than AODV.

VCPS (Vehicular Cyber Physical Systems) is a special kind of networked cyber physical system in which each vehicle is regarded as a communication unit. Vehicle's movement is restricted by road and environment in VCPS, while traditional random mobility model and waypoint mobility model cannot reflect the realistic vehicle traces. In VCPS, with the high speed of vehicles, the network topology undergoing tremendous changes all the time, which greatly undermines the stability of communication between vehicles. The diversity and complexity of traffic scenarios in VCPS have also increased the difficulty of designing an efficient and stable routing protocol. In this paper, we creatively combine SDN (Software Defined Networking) and VCPS together and propose a new VCPS communication architecture, which enable VCPS to be manageable by remote controller. SD-VCPS can flexibly change routing policies depending on different traffic scenes or traffic periods, adjusting the topology of VCPS to adapt to different network requirements. We further present a new location-based routing protocol for SD-VCPS, and corroborate the efficiency of our proposed framework by experiments using network simulator NS3.

With the increase of multicast data applications, research interests have focused on the design of congestion control schemes for multicast communications. This paper describes a novel control-theoretic multicast congestion control scheme, which is based on the distributed self-tuning proportional plus integrative (SPI) controller. The control parameters can be designed to ensure the stability of the control loop in terms of source rate. The distributed explicit rate SPI overcomes the vulnerability that suffers from the heterogeneous multicast receivers. It is suggested that the congestion controller is located at the multipoint-to-multipoint multicast source to regulate the transmission rate. We further analyze the theoretical aspects of the proposed algorithm, and show how the control mechanism can be used to design a controller to support multicast transmissions. Simulation results demonstrate the efficiency of the proposed scheme in terms of system stability and fast response of the buffer occupancy, as well as controlled sending rates, low packet loss, and high scalability