Fang Wang

Peng Fang, Arijit Khan, Siqiang Luo et al.

Graph embedding maps graph nodes to low-dimensional vectors, and is widely adopted in machine learning tasks. The increasing availability of billion-edge graphs underscores the importance of learning efficient and effective embeddings on large graphs, such as link prediction on Twitter with over one billion edges. Most existing graph embedding methods fall short of reaching high data scalability. In this paper, we present a general-purpose, distributed, information-centric random walk-based graph embedding framework, DistGER, which can scale to embed billion-edge graphs. DistGER incrementally computes information-centric random walks. It further leverages a multi-proximity-aware, streaming, parallel graph partitioning strategy, simultaneously achieving high local partition quality and excellent workload balancing across machines. DistGER also improves the distributed Skip-Gram learning model to generate node embeddings by optimizing the access locality, CPU throughput, and synchronization efficiency. Experiments on real-world graphs demonstrate that compared to state-of-the-art distributed graph embedding frameworks, including KnightKing, DistDGL, and Pytorch-BigGraph, DistGER exhibits 2.33x-129x acceleration, 45% reduction in cross-machines communication, and > 10% effectiveness improvement in downstream tasks.

Yuncong Li, Fang Wang, Wenjun Zhang et al.

Aspect Sentiment Triplet Extraction (ASTE) aims to extract aspect term, sentiment and opinion term triplets from sentences and tries to provide a complete solution for aspect-based sentiment analysis (ABSA). However, some triplets extracted by ASTE are confusing, since the sentiment in a triplet extracted by ASTE is the sentiment that the sentence expresses toward the aspect term rather than the sentiment of the aspect term and opinion term pair. In this paper, we introduce a more fine-grained Aspect-Sentiment-Opinion Triplet Extraction (ASOTE) Task. ASOTE also extracts aspect term, sentiment and opinion term triplets. However, the sentiment in a triplet extracted by ASOTE is the sentiment of the aspect term and opinion term pair. We build four datasets for ASOTE based on several popular ABSA benchmarks. We propose a Position-aware BERT-based Framework (PBF) to address this task. PBF first extracts aspect terms from sentences. For each extracted aspect term, PBF first generates aspect term-specific sentence representations considering both the meaning and the position of the aspect term, then extracts associated opinion terms and predicts the sentiments of the aspect term and opinion term pairs based on the sentence representations. Experimental results on the four datasets show the effectiveness of PBF.

Wenpeng He, Dan Feng, Fang Wang et al.

Memory security and reliability are two of the major design concerns in cloud computing systems. State-of-the-art memory security-reliability co-designs (e.g. Synergy) have achieved a good balance on performance, confidentiality, integrity, and reliability. However, these works merely rely on encryption to ensure data confidentiality, which has been proven unable to prevent information leakage from memory access patterns. Ring ORAM is an attractive confidential protection protocol to hide memory access patterns to the untrusted storage system. Unfortunately, it does not compatible with the security-reliability co-designs. A forced combination would result in more severe performance loss. In this paper, we propose IRO, an Integrity and Reliability enhanced Ring ORAM design. To reduce the overhead of integrity verification, we propose a low overhead integrity tree RIT and use a Minimum Update Subtree Tree (MUST) to reduce metadata update overhead. To improve memory reliability, we present Secure Replication to provide channel-level error resilience for the ORAM tree and use the mirrored channel technique to guarantee the reliability of the MUST. Last, we use the error correction pointer (ECP) to repair permanent memory cell fault to further improve device reliability and lifetime. A compact metadata design is used to reduce the storage and consulting overhead of the ECP. IRO provides strong security and reliability guarantees, while the resulting storage and performance overhead is very small. Our evaluation shows that IRO only increases 7.54% execution time on average over the Baseline under two channels four AES-GCM units setting. With enough AES-GCM units to perform concurrent MAC computing, IRO can reduce 2.14% execution time of the Baseline.